meminit-docops

Instructions for adding Meminit to an existing repository and managing governed documentation. Meminit is a tool for checking, creating, indexing, and maintaining structured project documents.

In plain words
What is it for?
Use them to migrate a repository, scan or fix documentation, create documents such as specifications and runbooks, set up checks in CI or pre-commit hooks, and look up document references.
Why use it?
They help keep documents compliant over time and reduce the risk of changing documentation without first reviewing the effects.

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/gitcmurf/revrem/meminit-docops
Any agent
npx skills add GitCmurf/revrem --skill meminit-docops
Clone the repo
git clone --depth 1 https://github.com/GitCmurf/revrem

Made for: Claude Code, Codex.

Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,121 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 $0.00071 $0.03121
Opus 5 $0.00036 $0.01561
Sonnet 5 $0.00014 $0.00624
Haiku 4.5 $0.00007 $0.00312

Measured yesterday against content hash 6062611d4b9f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

meminit-docops 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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/meminit_brownfield_plan.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.agents/skills/meminit-docops/SKILL.md · 344 lines

How it starts

The opening of the file, as written. The whole thing — 344 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Meminit DocOps Skill

Purpose

This skill teaches Codex how to use meminit to:

  • retrofit Meminit into an existing repository (brownfield migration), and
  • keep documentation compliant over time (local + CI gates).

It does not decide when your repo should adopt DocOps; that policy belongs in AGENTS.md and CI settings.

When to Use

Activate this skill when the user asks to:

  • Retrofit Meminit into an existing repo (brownfield migration).
  • Enforce DocOps compliance — check, fix, or audit governed documents.
  • Create governed documents — e.g. ADRs, PRDs, specs, runbooks via meminit new.
  • Troubleshoot documentation violations — diagnose and resolve meminit check failures.
  • Set up CI gates or pre-commit hooks for DocOps enforcement.
  • Resolve or look up document IDs using the Meminit index.

Safety rules (non-negotiable)

  1. Prefer read-only commands first: scan, doctor, check.
  2. Never run a write operation (fix --no-dry-run, fix --plan <PLAN_PATH> --no-dry-run, migrate-ids --no-dry-run, migrate-ids --rewrite-references, protocol sync --no-dry-run, or any rename/rewrite) without:
    • showing a dry-run preview, and
    • explicit user confirmation.
  3. Never attempt to “fix” semantic governance manually (ownership, approvals, status promotion) without asking.
  4. Do not introduce fake Markdown links like [text](path) unless the target exists.
  5. Prefer --format json for automation, treat STDOUT as machine output, and keep verbose reasoning on STDERR only.
  6. For brownfield repos, prefer plan-driven changes (scan --plan then fix --plan) over ad hoc write operations.

Quick command map

  • Initialization: meminit init
  • Repo readiness: meminit doctor --format json
  • Repo discovery: meminit context --format json (add --deep for per-namespace document counts)
  • Compliance: meminit check --format json (add --strict to promote warnings to errors)
  • Generate migration plan: meminit scan --plan <PLAN_PATH> --format json
  • Safe preview: meminit fix --dry-run --format json
  • Safe preview from plan: meminit fix --plan <PLAN_PATH> --format json (add --namespace <NS> for monorepo safety)
  • Apply mechanical fixes: meminit fix --no-dry-run --format json
  • Apply plan: meminit fix --plan <PLAN_PATH> --no-dry-run --format json (add --namespace <NS> for monorepo safety)
  • Migration planning: meminit scan --format json
  • Create governed doc: meminit new <TYPE> <TITLE> --format json (key flags: --owner, --area, --description, --status, --keywords, --related-ids, --id, --dry-run, --namespace)
  • Type discovery: meminit new --list-types --format json
  • ADR shortcut: meminit adr new <TITLE> --format json
  • Migrate legacy IDs: meminit migrate-ids --dry-run --format json (add --rewrite-references to update cross-refs)
  • Pre-commit hook: meminit install-precommit --root .
  • Org profile helpers (optional): meminit org status --format json, meminit org vendor --format json
  • Index + resolution:
    • meminit index --format json
    • meminit resolve <DOCUMENT_ID> --format json
    • meminit identify <PATH> --format json
    • meminit link <DOCUMENT_ID> --format json
  • Protocol governance:
    • meminit protocol check --format json (drift detection for governed assets)
    • meminit protocol sync --format json (preview-only by default; add --no-dry-run to apply)

Read the full file on GitHub · 344 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 344 lines · 71 tokens per session scan A 6062611d4b9f

Subscribe to this mod's changes

meminit-docops is a skill published in the GitHub repository GitCmurf/revrem (1 stars, last pushed 15d ago), licensed Apache-2.0. It adds 71 tokens to every session and 3,121 once invoked, about $0.0004 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.