git-memento-workflow

git-memento-workflow is a skill for Claude Code, Codex from mandel-macaque/memento. It costs 69 tokens per session (1,154 once invoked), scanned A, original, MIT.

A workflow for using git-memento with a repository. Git-memento stores an AI session transcript as a note attached to a Git commit and can sync that note to a remote repository.

In plain words
What is it for?
Use it to configure Codex or Claude, create commits with attached session notes, verify those notes, and share them with a remote.
Why use it?
It preserves the reasoning and conversation behind a code change, making AI-assisted commits easier to understand later.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Codex.

Good fit Use it to configure Codex or Claude, create commits with attached session notes, verify those notes, and share them with a remote.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mandel-macaque/memento/git-memento-workflow
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.

Any agent
npx skills add mandel-macaque/memento --skill git-memento-workflow
Clone the repo
git clone --depth 1 https://github.com/mandel-macaque/memento

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for git-memento-workflow

README.md
[![agentmods](https://agentmods.dev/badge/skills/mandel-macaque/memento/git-memento-workflow.svg)](https://agentmods.dev/skills/mandel-macaque/memento/git-memento-workflow)
Your own site
<a href="https://agentmods.dev/skills/mandel-macaque/memento/git-memento-workflow"><img src="https://agentmods.dev/badge/skills/mandel-macaque/memento/git-memento-workflow.svg" alt="Measured on agentmods" height="20"></a>
Per session 69 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,154 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00069 $0.01154
Opus 5 $0.00034 $0.00577
Sonnet 5 $0.00014 $0.00231
Haiku 4.5 $0.00007 $0.00115

Measured 8d ago against content hash 3f341678210b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

git-memento-workflow 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 8d ago.

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/git-memento-workflow/SKILL.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Git Memento Workflow

Run this workflow whenever work must be committed with an AI session note.

1. Preflight

  • Confirm repository status with git status --short and branch with git branch --show-current.
  • Confirm git memento is available: git memento help.
  • If unavailable, install git-memento into a directory on PATH and re-check.

2. Initialize Once Per Repository

  • Check configuration: git config --local --get memento.provider.
  • If missing, run git memento init codex or git memento init claude.
  • If provider CLI shape differs from expected sessions get/list --json, configure adapter command in local git config:
    • git config --local memento.<provider>.bin <adapter-or-cli-path>
    • git config --local memento.<provider>.getArgs '<args with {id} placeholder>'
    • git config --local memento.<provider>.listArgs '<list args>'
  • For summary mode, configure provider summary execution if defaults do not match your environment:
    • git config --local memento.<provider>.summary.bin <adapter-or-cli-path>
    • git config --local memento.<provider>.summary.args '<args with {prompt}, optionally {skill} and {sessionId}>'

3. Resolve Session ID

  • Prefer explicit session id from the user.
  • For Codex in this environment, default to CODEX_THREAD_ID when present.
  • Validate retrieval before commit by running provider command manually if needed.

4. Create Memento Commit or Amend

  • Stage files as needed (git add ...).
  • Run commit through memento so note attachment happens in the same flow:
    • git memento commit <session-id> -m "<subject>"
    • Optional summary mode: git memento commit <session-id> --summary-skill <skill|default> -m "<subject>"
  • For amend flows:
    • git memento amend -m "<amended-subject>" to carry forward existing note(s) onto the amended commit.
    • git memento amend <session-id> -m "<amended-subject>" to carry forward existing note(s) and append a new session.
    • Optional summary mode: git memento amend <session-id> --summary-skill <skill|default> -m "<amended-subject>"
  • Summary mode behavior:
    • The CLI generates a markdown summary using the configured provider command.
    • It prints the generated summary and requires explicit confirmation.
    • If rejected, it asks for a user prompt and regenerates.
    • It writes the summary into refs/notes/commits and stores the full session in refs/notes/memento-full-audit.
  • Backward compatibility:
    • Legacy single-session notes are preserved.
    • When append is needed, legacy notes are upgraded into the versioned multi-session envelope so no prior session content is lost.
  • For longer body, use embedded newlines in -m or omit -m to use editor.

Read the full file on GitHub · 83 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. 8d ago First seen · 83 lines · 69 tokens per session scan A 3f341678210b

Subscribe to this mod's changes

git-memento-workflow is a skill published in the GitHub repository mandel-macaque/memento (449 stars, last pushed 5mo ago), licensed MIT. It adds 69 tokens to every session and 1,154 once invoked, about $0.0003 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 2026-08-30.