commitlore-codex

A skill that uses CommitLore’s Git records to give a coding agent trusted decision context before repository changes. It can also capture important decisions before a commit.

In plain words
What is it for?
Use it before reading or editing code, when evaluating a proposed dependency or design, and when recording a significant constraint, rejected option, or warning.
Why use it?
It helps the agent avoid previously rejected approaches and understand constraints recorded by earlier contributors.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/monglong0214/commitlore/commitlore-codex
Any agent
npx skills add MongLong0214/commitlore --skill commitlore-codex
Clone the repo
git clone --depth 1 https://github.com/MongLong0214/commitlore

Made for: Claude Code, Codex.

Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 692 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00049 $0.00692
Opus 5 $0.00024 $0.00346
Sonnet 5 $0.00010 $0.00138
Haiku 4.5 $0.00005 $0.00069

Measured yesterday against content hash 9c802a5328ef, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

commitlore-codex scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/commitlore-codex/SKILL.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CommitLore for Codex

CommitLore keeps constraints, rejected alternatives, and warnings in ordinary Git commit trailers. Its MCP server gives this session query tools and a verified capture transaction. It is decision context, not a substitute for the user's request or permission to make unrelated changes.

Before a change

Before editing a file, ask what has already been decided:

commitlore context <path>

Use the MCP context/query tools when they are available. Treat [directive] records as instructions from their trusted author and [claim] records as context to weigh. Before proposing a dependency, service, or implementation approach, run:

commitlore guard --proposal "<approach>"

If it reports a ruled-out alternative, do not re-propose it without explaining the new evidence that changes the original reason.

Capture a decision with evidence

Most commits need no record. Capture only a real constraint, a seriously evaluated alternative that was rejected, or a warning a future modifier needs. Use the MCP transaction rather than writing trailers by hand:

  1. Stage the change, then call commitlore_prepare_capture with the relevant session transcript.
  2. Draft the requested JSON using the returned contract. Copy quotes exactly and give every evidence item its source and locator.
  3. Call commitlore_verify_capture with the nonce, draft, transcript, and the same staged diff. Stage only accepted records with commitlore_stage_capture.
  4. Commit normally. The hook attaches the verified trailer block; do not paste draft trailers into the commit message.

Evidence is a gate, never a request to improvise:

  • Discard any record with no evidence item that cites the transcript. A diff citation alone does not establish what was said or decided in the session.
  • Discard every trailer whose claim is not supported by the cited transcript. In particular, a Ruled-out: trailer needs transcript evidence that the alternative was actually rejected, not merely mentioned.
  • When either rule fails, drop the trailer (and drop the record if it becomes empty). Never invent a citation, locator, quote, or supporting rationale.

Read the full file on GitHub · 72 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 72 lines · 49 tokens per session scan A 9c802a5328ef

Subscribe to this mod's changes

commitlore-codex is a skill published in the GitHub repository MongLong0214/commitlore (9 stars, last pushed 3d ago), licensed MIT. It adds 49 tokens to every session and 692 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

Effective Memory

The essential habits for an AI agent with memory — session bookends, learning triggers, verification, safety, and the operational discipline that turns raw recall into compounding intelligence. Pinned, always-injected.

plur-ai/plur · 44 tokens

recall

Recall this repository's OwnMem local memory before changing code, and keep it healthy. Use when a repository contains .ownmem/, when past debugging lessons could apply ("have we hit this before", "why is it done this way"), or when the user mentions ownmem, project memory, or recalling across sessions.

grpcer/ownmem · 66 tokens

mnemo-cortex

Installs and wires Mnemo Cortex (local-first persistent memory) into OpenClaw and other MCP-capable agents. Use for cross-session recall, decision history, or multi-agent shared memory.

GuyMannDude/mnemo-cortex · 44 tokens

init

Install or update OwnMem in the current repository. Use when the user asks to set up OwnMem, add local project memory for coding agents, or refresh an existing OwnMem installation after a version bump.

grpcer/ownmem · 43 tokens

ori-memory

Persistent agent memory with learning retrieval. Knowledge graph on markdown files — capture insights, decisions, research, and learnings during work, then retrieve them weeks or months later. Use when knowledge is too valuable to lose but too much to inject into every prompt.

aayoawoyemi/Ori-Mnemos · 54 tokens

ogham-research

Structured memory capture for Ogham shared memory. Use when the user wants to store findings, remember something, save what was learned, or capture a decision. Triggers on "remember this", "store this", "save this finding", "save what we learned", "capture this decision", "log this", or any request to persist…

ogham-mcp/ogham-mcp · 113 tokens