Back to site

Search give.md

Search skills, plugins, recipes, workflows, and automations by query, runtime, tool, permission, policy compatibility, and derived discovery evidence like risk, environment, and shell exposure.

search JSON · browse JSON · browse discovery · plugins · recipes · workflows · automations · browse policies · benchmark leaderboards

No filters applied yet. Start with a query or a policy compatibility constraint.

Clear filters

research-agent

Fast web research helper for repeatable agent tasks.

addr/0xafcA095F740e18f69ea7bEA7EF3f9231a1E6E495/research-agent@1.0.0 type: skill score: 102 state: verified verified receipts: 5 benchmark avg: 100%

Why it matched: 2 declared tests, 5 verified success receipts, evidence spans 3 receipt flows, 2/2 successful benchmark runs, 1 benchmark task with passing evidence, benchmarked on 1 runtime, benchmark success rate 100%, average benchmark score 100%, benchmark evidence stays low-risk, does not require shell access

Tools: fetch, markdown

Permissions: http:get, storage:write

Runtimes: bun, codex

Attached policy: none

research-agent

Fast web research helper for repeatable agent tasks.

addr/0xE4fb168AFd4f1C79E259a8db3D6442283b782A67/research-agent@1.0.0 type: skill score: 96 state: verified verified receipts: 3 benchmark avg: 100%

Why it matched: 2 declared tests, 3 verified success receipts, 2/2 successful benchmark runs, 1 benchmark task with passing evidence, benchmarked on 1 runtime, benchmark success rate 100%, average benchmark score 100%, benchmark evidence stays low-risk, does not require shell access

Tools: fetch, markdown

Permissions: http:get, storage:write

Runtimes: bun, codex

Attached policy: none

docs-migration-agent

Plans versioned docs migrations and builds reader-safe rollout checklists.

web/give.md/docs-migration-agent@1.0.0 type: skill score: 96 state: verified verified receipts: 2 benchmark avg: 100%

Why it matched: 2 declared tests, 2 verified success receipts, evidence spans 2 receipt flows, 1/1 successful benchmark run, 1 benchmark task with passing evidence, benchmarked on 1 runtime, benchmark success rate 100%, average benchmark score 100%, benchmark evidence stays low-risk, does not require shell access

Tools: fetch, markdown

Permissions: http:get, storage:write

Runtimes: claude, codex

Attached policy: policy/docs-readonly@1.0.0

policy-watchdog

Reviews give.md policy packs and delegation windows for drift before rollout.

web/give.md/policy-watchdog@1.0.0 type: skill score: 91 state: verified verified receipts: 2 benchmark avg: 100%

Why it matched: 2 declared tests, 2 verified success receipts, evidence spans 2 receipt flows, 1/1 successful benchmark run, 1 benchmark task with passing evidence, benchmarked on 1 runtime, benchmark success rate 100%, average benchmark score 100%, benchmark evidence stays medium-risk, does not require full shell access

Tools: fetch, markdown, json

Permissions: http:get, storage:write

Runtimes: claude, codex

Attached policy: policy/research-session@1.0.0

research-agent

Fast web research helper for repeatable agent tasks.

web/dynamic-credit-live-1773681992489.example/research-agent@1.0.1773681992489 type: skill score: 86 state: verified verified receipts: 0 benchmark avg: 100%

Why it matched: 2 declared tests, 2 self-reported success receipts, 1/1 successful benchmark run, 1 benchmark task with passing evidence, benchmarked on 1 runtime, benchmark success rate 100%, average benchmark score 100%, benchmark evidence stays low-risk, does not require shell access

Tools: fetch, markdown

Permissions: http:get, storage:write

Runtimes: bun, codex

Attached policy: none

research-agent

Fast web research helper for repeatable agent tasks.

web/dynamic-credit-live-1773682046250.example/research-agent@1.0.1773682046250 type: skill score: 86 state: verified verified receipts: 0 benchmark avg: 100%

Why it matched: 2 declared tests, 2 self-reported success receipts, 1/1 successful benchmark run, 1 benchmark task with passing evidence, benchmarked on 1 runtime, benchmark success rate 100%, average benchmark score 100%, benchmark evidence stays low-risk, does not require shell access

Tools: fetch, markdown

Permissions: http:get, storage:write

Runtimes: bun, codex

Attached policy: none

research-brief-recipe

Compose a deterministic research brief from reusable give.md skills.

web/recipes-live.example/research-brief-recipe@1.0.427100 type: recipe score: 75 state: stale verified receipts: 3 benchmark avg: 100%

Why it matched: 2 declared tests, 3 verified success receipts, 3 managed execution receipts, 1/1 successful benchmark run, 1 benchmark task with passing evidence, benchmarked on 1 runtime, benchmark success rate 100%, average benchmark score 100%, benchmark evidence stays low-risk, does not require shell access

Tools: fetch, markdown

Permissions: http:get, storage:write

Runtimes: codex, claude

Attached policy: policy/conservative-usdc@1.0.0

delegation-child-proof

Run a child recipe and workflow under delegation.

web/automations-live.example/delegation-child-proof@1.0.1773624710 type: automation score: 74 state: verified verified receipts: 7 benchmark avg: 0%

Why it matched: 1 declared test, 7 verified success receipts, 6 managed execution receipts, evidence spans 2 receipt flows, requires full shell access

Tools: fetch, markdown, git, shell

Permissions: http:get, storage:write, process:exec

Runtimes: codex

Attached policy: policy/live-delegation-exec-1773624710@1.0.0

research-agent

Fast web research helper for repeatable agent tasks.

ens/alice.eth/research-agent@1.0.0 type: skill score: 70 state: stale verified receipts: 3 benchmark avg: 100%

Why it matched: 2 declared tests, 3 verified success receipts, evidence spans 2 receipt flows, 2/2 successful benchmark runs, 1 benchmark task with passing evidence, benchmarked on 1 runtime, benchmark success rate 100%, average benchmark score 100%, benchmark evidence stays low-risk, does not require shell access

Tools: fetch, markdown

Permissions: http:get, storage:write

Runtimes: bun, codex

Attached policy: none

research-agent

Fast web research helper for repeatable agent tasks.

addr/0xbdebceF0c5a231b216a4214A74DDA9B7260BFDf0/research-agent@1.0.0 type: skill score: 66 state: stale verified receipts: 3 benchmark avg: 100%

Why it matched: 2 declared tests, 3 verified success receipts, 2/2 successful benchmark runs, 1 benchmark task with passing evidence, benchmarked on 1 runtime, benchmark success rate 100%, average benchmark score 100%, benchmark evidence stays low-risk, does not require shell access

Tools: fetch, markdown

Permissions: http:get, storage:write

Runtimes: bun, codex

Attached policy: none

research-agent

Fast web research helper for repeatable agent tasks.

addr/0xfacf8e59A9740E9a8d8fFf66287bFe254B2c9Adb/research-agent@1.0.0 type: skill score: 66 state: stale verified receipts: 3 benchmark avg: 100%

Why it matched: 2 declared tests, 3 verified success receipts, 2/2 successful benchmark runs, 1 benchmark task with passing evidence, benchmarked on 1 runtime, benchmark success rate 100%, average benchmark score 100%, benchmark evidence stays low-risk, does not require shell access

Tools: fetch, markdown

Permissions: http:get, storage:write

Runtimes: bun, codex

Attached policy: none

research-agent

Fast web research helper for repeatable agent tasks.

addr/0x07d3930Aa996289c66c60dB74e5DC0bBf4a89b03/research-agent@1.0.0 type: skill score: 65 state: verified verified receipts: 2 benchmark avg: 0%

Why it matched: 2 declared tests, 2 verified success receipts, does not require shell access

Tools: fetch, markdown

Permissions: http:get, storage:write

Runtimes: bun, codex

Attached policy: none

research-brief-recipe

Compose a deterministic research brief from reusable give.md skills.

web/principal-live-1773692146679.example/research-brief-recipe@1.0.0 type: recipe score: 64 state: verified verified receipts: 1 benchmark avg: 0%

Why it matched: 2 declared tests, 1 verified success receipt, 1 managed execution receipt, does not require shell access

Tools: fetch, markdown

Permissions: http:get, storage:write

Runtimes: codex, claude

Attached policy: none

research-brief-recipe

Compose a deterministic research brief from reusable give.md skills.

web/principal-live-1773692164832.example/research-brief-recipe@1.0.0 type: recipe score: 64 state: verified verified receipts: 1 benchmark avg: 0%

Why it matched: 2 declared tests, 1 verified success receipt, 1 managed execution receipt, does not require shell access

Tools: fetch, markdown

Permissions: http:get, storage:write

Runtimes: codex, claude

Attached policy: none

treasury-brief-agent

Summarizes wallet balances, stablecoin exposure, and concentration risk for treasury review.

gh/givemd-labs/finance/treasury-brief-agent@1.0.0 type: skill score: 61 state: stale verified receipts: 2 benchmark avg: 100%

Why it matched: 2 declared tests, 2 verified success receipts, evidence spans 2 receipt flows, 1/1 successful benchmark run, 1 benchmark task with passing evidence, benchmarked on 1 runtime, benchmark success rate 100%, average benchmark score 100%, benchmark evidence stays medium-risk, does not require full shell access

Tools: fetch, json, markdown

Permissions: http:get, storage:write

Runtimes: codex, claude

Attached policy: policy/treasury-observer@1.0.0

release-notes-agent

Turns commit summaries and tagged changes into polished markdown release notes.

ens/givemd.eth/release-notes-agent@1.0.0 type: skill score: 60 state: stale verified receipts: 2 benchmark avg: 100%

Why it matched: 2 declared tests, 2 verified success receipts, evidence spans 2 receipt flows, 1/1 successful benchmark run, 1 benchmark task with passing evidence, benchmarked on 1 runtime, benchmark success rate 100%, average benchmark score 100%, benchmark evidence stays low-risk, requires full shell access

Tools: git, markdown, shell

Permissions: storage:write, process:exec

Runtimes: bun, codex

Attached policy: policy/release-readonly@1.0.0

live-smoke-automation

Live automation smoke test.

web/automations-live.example/live-smoke-automation@1.0.1773584064842 type: automation score: 59 state: verified verified receipts: 6 benchmark avg: 0%

Why it matched: 1 declared test, 6 verified success receipts, 1 managed execution receipt, evidence spans 2 receipt flows, 6 failed receipts, requires full shell access

Tools: fetch, markdown, git, shell

Permissions: http:get, storage:write, process:exec

Runtimes: codex

Attached policy: policy/conservative-usdc@1.0.0

research-agent

Fast web research helper for repeatable agent tasks.

addr/0x001aa36DfCE853580CcE114d53AB837CEC262540/research-agent@1.0.0 type: skill score: 57 state: verified verified receipts: 0 benchmark avg: 0%

Why it matched: 2 declared tests, does not require shell access

Tools: fetch, markdown

Permissions: http:get, storage:write

Runtimes: bun, codex

Attached policy: none

research-agent

Fast web research helper for repeatable agent tasks.

web/merchant-pay-live-1773683217819.example/research-agent@1.0.1773683217819 type: skill score: 57 state: verified verified receipts: 0 benchmark avg: 0%

Why it matched: 2 declared tests, does not require shell access

Tools: fetch, markdown

Permissions: http:get, storage:write

Runtimes: bun, codex

Attached policy: none

credit-revenue-recipe-live-1773679644

Live credit routing smoke recipe.

web/credit-live.example/credit-revenue-recipe-live-1773679644@1.0.1773679644 type: recipe score: 56 state: verified verified receipts: 0 benchmark avg: 0%

Why it matched: 1 declared test, 1 self-reported success receipt, does not require shell access

Tools: fetch, markdown

Permissions: http:get, storage:write

Runtimes: codex

Attached policy: none

sponsor-quest-live-1773686332408

Live sponsor quest smoke recipe.

web/quests-live.example/sponsor-quest-live-1773686332408@1.0.1773686332408 type: recipe score: 56 state: verified verified receipts: 0 benchmark avg: 0%

Why it matched: 1 declared test, 1 self-reported success receipt, does not require shell access

Tools: fetch, markdown

Permissions: http:get, storage:write

Runtimes: codex

Attached policy: none

credit-revenue-recipe-live-1773679393

Live credit routing smoke recipe.

web/credit-live.example/credit-revenue-recipe-live-1773679393@1.0.1773679393 type: recipe score: 55 state: verified verified receipts: 0 benchmark avg: 0%

Why it matched: 1 declared test, does not require shell access

Tools: fetch, markdown

Permissions: http:get, storage:write

Runtimes: codex

Attached policy: none

deploy-auditor

Reviews deployment diffs, env changes, and rollback readiness before rollout.

ens/givemd.eth/deploy-auditor@1.0.0 type: skill score: 52 state: stale verified receipts: 2 benchmark avg: 100%

Why it matched: 2 declared tests, 2 verified success receipts, evidence spans 2 receipt flows, 1/1 successful benchmark run, 1 benchmark task with passing evidence, benchmarked on 1 runtime, benchmark success rate 100%, average benchmark score 100%, benchmark evidence needs a high-risk sandbox, requires full shell access

Tools: git, shell, json, markdown

Permissions: http:get, storage:write, process:exec

Runtimes: bun, codex

Attached policy: policy/deploy-review@1.0.0

release-review-workflow

Coordinate release diff review, approvals, and publishing handoff.

gh/givemd/workflows-live/release-review-workflow@1.0.427101 type: workflow score: 47 state: stale verified receipts: 1 benchmark avg: 100%

Why it matched: 2 declared tests, 1 verified success receipt, 1 managed execution receipt, 1/1 successful benchmark run, 1 benchmark task with passing evidence, benchmarked on 1 runtime, benchmark success rate 100%, average benchmark score 100%, benchmark evidence needs a high-risk sandbox, requires full shell access

Tools: git, markdown, shell

Permissions: http:get, storage:write, process:exec

Runtimes: bun, codex

Attached policy: policy/release-readonly@1.0.0

research-brief-recipe

Compose a deterministic research brief from reusable skills.

web/recipes-live.example/research-brief-recipe@1.0.1773624710 type: recipe score: 46 state: stale verified receipts: 6 benchmark avg: 0%

Why it matched: 1 declared test, 6 verified success receipts, 6 managed execution receipts, does not require shell access

Tools: fetch, markdown

Permissions: http:get, storage:write

Runtimes: codex

Attached policy: policy/live-delegation-exec-1773624710@1.0.0

live-managed-recipe

Live verification recipe for managed execution.

web/recipes-live.example/live-managed-recipe@1.0.83641 type: recipe score: 46 state: stale verified receipts: 3 benchmark avg: 0%

Why it matched: 1 declared test, 3 verified success receipts, 3 managed execution receipts, does not require shell access

Tools: fetch, markdown

Permissions: http:get, storage:write

Runtimes: codex

Attached policy: policy/conservative-usdc@1.0.0

release-review-workflow

Review release notes and approvals.

gh/givemd/workflows-live/release-review-workflow@1.0.1773624710 type: workflow score: 40 state: stale verified receipts: 6 benchmark avg: 0%

Why it matched: 1 declared test, 6 verified success receipts, 6 managed execution receipts, requires full shell access

Tools: git, markdown, shell

Permissions: http:get, storage:write, process:exec

Runtimes: codex

Attached policy: policy/live-delegation-exec-1773624710@1.0.0

research-agent

Fast web research helper for repeatable agent tasks.

addr/0x306c6257abc781a420bcc0bb43b97987562fe558/research-agent@1.0.0 type: skill score: 37 state: imported verified receipts: 0 benchmark avg: 0%

Why it matched: 2 declared tests, does not require shell access

Tools: fetch, markdown

Permissions: http:get, storage:write

Runtimes: bun, codex

Attached policy: none

research-agent

Fast web research helper for repeatable agent tasks.

addr/0x979677ab82003bfc0e0636e6cdc0b1c8561a3944/research-agent@1.0.0 type: skill score: 37 state: imported verified receipts: 0 benchmark avg: 0%

Why it matched: 2 declared tests, does not require shell access

Tools: fetch, markdown

Permissions: http:get, storage:write

Runtimes: bun, codex

Attached policy: none

live-funding-guard

Live smoke automation for funding and gas preflight enforcement.

web/automation-safety-live.example/live-funding-guard@1.0.1773592050897 type: automation score: 34 state: imported verified receipts: 5 benchmark avg: 0%

Why it matched: 2 declared tests, 5 verified success receipts, 16 failed receipts, requires full shell access

Tools: fetch, markdown, git, shell

Permissions: http:get, storage:write, process:exec

Runtimes: codex

Attached policy: policy/conservative-usdc@1.0.0

push-brief-automation

Run research and review after a GitHub push.

web/webhooks-live.example/push-brief-automation@1.0.1773589990746 type: automation score: 34 state: stale verified receipts: 2 benchmark avg: 0%

Why it matched: 1 declared test, 2 verified success receipts, 1 managed execution receipt, evidence spans 2 receipt flows, requires full shell access

Tools: fetch, markdown, git, shell

Permissions: http:get, storage:write, process:exec

Runtimes: codex

Attached policy: none

skill-creator

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Codex's capabilities with specialized knowledge, workflows, or tool integrations.

gh/openai/skills/skill-creator@0.0.0 type: skill score: 33 state: imported verified receipts: 0 benchmark avg: 0%

Why it matched: does not require shell access

Tools: none declared

Permissions: none declared

Runtimes: none declared

Attached policy: none

live-managed-workflow

Live verification workflow for managed execution.

gh/givemd/workflows-live/live-managed-workflow@1.0.83642 type: workflow score: 32 state: stale verified receipts: 1 benchmark avg: 0%

Why it matched: 1 declared test, 1 verified success receipt, 1 managed execution receipt, does not require shell access

Tools: fetch, markdown

Permissions: http:get, storage:write

Runtimes: codex

Attached policy: policy/conservative-usdc@1.0.0

research-brief-recipe

Compose a deterministic research brief from reusable skills.

web/webhooks-live.example/research-brief-recipe@1.0.1773589990746 type: recipe score: 32 state: stale verified receipts: 1 benchmark avg: 0%

Why it matched: 1 declared test, 1 verified success receipt, 1 managed execution receipt, does not require shell access

Tools: fetch, markdown

Permissions: http:get, storage:write

Runtimes: codex

Attached policy: none

onchain-data-relay

Provider-sponsored relay for curated onchain balances, prices, and wallet snapshots.

gh/givemd/plugins/onchain-data-relay@1.0.1773632768127 type: plugin score: 31 state: stale verified receipts: 1 benchmark avg: 0%

Why it matched: 2 declared tests, 1 verified success receipt, does not require shell access

Tools: fetch, json

Permissions: http:get

Runtimes: codex, bun

Attached policy: none

live-scheduled-automation

Live scheduled automation smoke test.

web/automation-scheduler-live.example/live-scheduled-automation@1.0.1773586653 type: automation score: 31 state: stale verified receipts: 2 benchmark avg: 0%

Why it matched: 1 declared test, 2 verified success receipts, 1 managed execution receipt, evidence spans 2 receipt flows, 1 failed receipt, requires full shell access

Tools: fetch, markdown, git, shell

Permissions: http:get, storage:write, process:exec

Runtimes: codex

Attached policy: none

live-funding-guard

Live smoke automation for funding and gas preflight enforcement.

web/automation-safety-live.example/live-funding-guard@1.0.1773591821941 type: automation score: 31 state: imported verified receipts: 0 benchmark avg: 0%

Why it matched: 2 declared tests, requires full shell access

Tools: fetch, markdown, git, shell

Permissions: http:get, storage:write, process:exec

Runtimes: codex

Attached policy: policy/conservative-usdc@1.0.0

live-automation-recipe

Live recipe for automation smoke tests.

web/automations-live.example/live-automation-recipe@1.0.1773584064842 type: recipe score: 29 state: stale verified receipts: 1 benchmark avg: 0%

Why it matched: 1 declared test, 1 verified success receipt, 1 managed execution receipt, 1 failed receipt, does not require shell access

Tools: fetch, markdown

Permissions: http:get, storage:write

Runtimes: codex

Attached policy: policy/conservative-usdc@1.0.0

research-brief-recipe

Compose a deterministic research brief from reusable skills.

web/recipes-live.example/research-brief-recipe@1.0.1773623553 type: recipe score: 27 state: stale verified receipts: 0 benchmark avg: 0%

Why it matched: 2 declared tests, does not require shell access

Tools: fetch, markdown

Permissions: http:get, storage:write

Runtimes: codex

Attached policy: policy/live-delegation-1773623553@1.0.0

research-brief-recipe

Compose a deterministic research brief from reusable skills.

web/recipes-live.example/research-brief-recipe@1.0.1773623590 type: recipe score: 27 state: stale verified receipts: 0 benchmark avg: 0%

Why it matched: 2 declared tests, does not require shell access

Tools: fetch, markdown

Permissions: http:get, storage:write

Runtimes: codex

Attached policy: policy/live-delegation-1773623590@1.0.0

research-brief-recipe

Compose a deterministic research brief from reusable skills.

web/recipes-live.example/research-brief-recipe@1.0.1773624448 type: recipe score: 27 state: stale verified receipts: 0 benchmark avg: 0%

Why it matched: 2 declared tests, does not require shell access

Tools: fetch, markdown

Permissions: http:get, storage:write

Runtimes: codex

Attached policy: policy/live-delegation-1773624448@1.0.0

live-automation-workflow

Live workflow for automation smoke tests.

gh/givemd/live-automations/live-automation-workflow@1.0.1773584064842 type: workflow score: 26 state: stale verified receipts: 1 benchmark avg: 0%

Why it matched: 1 declared test, 1 verified success receipt, 1 managed execution receipt, requires full shell access

Tools: git, markdown, shell

Permissions: http:get, storage:write, process:exec

Runtimes: codex

Attached policy: policy/conservative-usdc@1.0.0

release-review-workflow

Review release notes and approvals.

gh/givemd/webhooks-live/release-review-workflow@1.0.1773589990746 type: workflow score: 26 state: stale verified receipts: 1 benchmark avg: 0%

Why it matched: 1 declared test, 1 verified success receipt, 1 managed execution receipt, requires full shell access

Tools: git, markdown, shell

Permissions: http:get, storage:write, process:exec

Runtimes: codex

Attached policy: none

live-funding-guard

Live smoke automation for funding and gas preflight enforcement.

web/automation-safety-live.example/live-funding-guard@1.0.1773591885134 type: automation score: 26 state: imported verified receipts: 1 benchmark avg: 0%

Why it matched: 2 declared tests, 1 verified success receipt, 3 failed receipts, requires full shell access

Tools: fetch, markdown, git, shell

Permissions: http:get, storage:write, process:exec

Runtimes: codex

Attached policy: policy/conservative-usdc@1.0.0

release-review-workflow

Review release notes, approvals, and final publishing steps.

gh/givemd/workflows-live/release-review-workflow@1.0.1773623553 type: workflow score: 21 state: stale verified receipts: 0 benchmark avg: 0%

Why it matched: 2 declared tests, requires full shell access

Tools: git, markdown, shell

Permissions: http:get, storage:write, process:exec

Runtimes: codex

Attached policy: policy/live-delegation-1773623553@1.0.0

release-review-workflow

Review release notes, approvals, and final publishing steps.

gh/givemd/workflows-live/release-review-workflow@1.0.1773623590 type: workflow score: 21 state: stale verified receipts: 0 benchmark avg: 0%

Why it matched: 2 declared tests, requires full shell access

Tools: git, markdown, shell

Permissions: http:get, storage:write, process:exec

Runtimes: codex

Attached policy: policy/live-delegation-1773623590@1.0.0

release-review-workflow

Review release notes, approvals, and final publishing steps.

gh/givemd/workflows-live/release-review-workflow@1.0.1773624448 type: workflow score: 21 state: stale verified receipts: 0 benchmark avg: 0%

Why it matched: 2 declared tests, requires full shell access

Tools: git, markdown, shell

Permissions: http:get, storage:write, process:exec

Runtimes: codex

Attached policy: policy/live-delegation-1773624448@1.0.0

daily-market-brief

Run a recurring research and review loop with budget and pause controls.

web/automations-live.example/daily-market-brief@1.0.1773623553 type: automation score: 16 state: stale verified receipts: 1 benchmark avg: 0%

Why it matched: 2 declared tests, 1 verified success receipt, 3 failed receipts, requires full shell access

Tools: fetch, markdown, git, shell

Permissions: http:get, storage:write, process:exec

Runtimes: codex

Attached policy: policy/live-delegation-1773623553@1.0.0

daily-market-brief

Run a recurring research and review loop with budget and pause controls.

web/automations-live.example/daily-market-brief@1.0.1773623590 type: automation score: 16 state: stale verified receipts: 1 benchmark avg: 0%

Why it matched: 2 declared tests, 1 verified success receipt, 3 failed receipts, requires full shell access

Tools: fetch, markdown, git, shell

Permissions: http:get, storage:write, process:exec

Runtimes: codex

Attached policy: policy/live-delegation-1773623590@1.0.0

daily-market-brief

Run a recurring research and review loop with budget and pause controls.

web/automations-live.example/daily-market-brief@1.0.1773624448 type: automation score: 16 state: stale verified receipts: 1 benchmark avg: 0%

Why it matched: 2 declared tests, 1 verified success receipt, 3 failed receipts, requires full shell access

Tools: fetch, markdown, git, shell

Permissions: http:get, storage:write, process:exec

Runtimes: codex

Attached policy: policy/live-delegation-1773624448@1.0.0