luisalima/agent-policy-kit

Repo-local operating policy and skills for coding agents

2Stars on the repository
9Mods indexed here, across every type
2mo agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

done

01

luisalima/agent-policy-kit

Skill Claude CodeCodex

Use before closing a task, raising a PR, pushing, or reporting completion.

not rated 2 2mo ago A 18 tokens original MIT

linters

02

luisalima/agent-policy-kit

Skill Claude CodeCodex

Use when a repo lacks a lint command for changed code, when adding a new language/toolchain, or when asked to improve static checks. Add relevant linters conservatively, using existing project tooling first, and avoid adding dependencies without a clear project fit.

not rated 2 2mo ago A 54 tokens original MIT

opentasks

03

luisalima/agent-policy-kit

Skill Claude CodeCodex

Maintain a lightweight docs/tasks/ repo convention for coding-agent tasks and open questions: bootstrap the folder, create task/question markdown files, update status, close or reopen items, list open work, and rebuild the derived index.

not rated 2 2mo ago A 48 tokens original MIT

security-review

04

luisalima/agent-policy-kit

Skill Claude CodeCodex

Use after substantial security-impacting implementation changes to review the branch diff for high-confidence vulnerabilities.

not rated 2 2mo ago A 21 tokens original MIT

slice

05

luisalima/agent-policy-kit

Skill Claude CodeCodex

Use before planning implementation to define the smallest demonstrable vertical slice.

not rated 2 2mo ago A 15 tokens original MIT

spike

06

luisalima/agent-policy-kit

Skill Claude CodeCodex

Use when behavior is not yet known and exploratory work is needed before TDD.

not rated 2 2mo ago A 19 tokens original MIT

tdd

07

luisalima/agent-policy-kit

Skill Claude CodeCodex

Use before writing source code for behavior with an assertable contract. Do not use for pure formatting, docs-only edits, or declared exploratory spikes.

not rated 2 2mo ago A 32 tokens original MIT

threat-model

08

luisalima/agent-policy-kit

Skill Claude CodeCodex

Use before security-relevant architecture work to model trust boundaries, assets, attacker capabilities, abuse paths, and mitigations.

not rated 2 2mo ago A 28 tokens original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: