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.
npx skills add toejough/engram --skill gitignore-narrowinggit clone --depth 1 https://github.com/toejough/engramWrote 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.
[](https://agentmods.dev/skills/toejough/engram/gitignore-narrowing)<a href="https://agentmods.dev/skills/toejough/engram/gitignore-narrowing"><img src="https://agentmods.dev/badge/skills/toejough/engram/gitignore-narrowing/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/toejough/engram/gitignore-narrowing"><img src="https://agentmods.dev/badge/skills/toejough/engram/gitignore-narrowing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00073 | $0.01002 |
| Opus 5.5 | $0.00029 | $0.00401 |
| Sonnet 5.5 | $0.00015 | $0.00200 |
| Haiku 4.5 | $0.00007 | $0.00100 |
Grade A, and why
gitignore-narrowing 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 28d 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.
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.
Gitignore Narrowing: Anchor Verification and Explicit Visible-Set Staging
Overview
Narrowing a .gitignore pattern (e.g. testdata/ -> testdata/rapid/) has two
independent failure modes: the new pattern can silently stop matching nested
paths (a gitignore anchoring gotcha), and the files it newly exposes can get
swept into a commit alongside unrelated untracked work if staged with a bare
git add -A/git add .. This skill is the verification-and-staging procedure
that catches both before anything is committed.
When to Use
Before shipping a narrowed or rewritten .gitignore pattern that makes some
previously-ignored files trackable. Triggers include:
- Tightening a broad ignore rule (e.g.
testdata/->testdata/rapid/) so only a subset stays ignored. - Any
.gitignoreedit expected to newly expose files in nested subdirectories, not just at the repo root. - About to stage the result of a
.gitignorenarrowing withgit add.
Procedure
- In a scratch repo, write the proposed replacement
.gitignorepattern. - Run
git check-ignore -q <path>against representative paths, including nested ones under subdirectories (e.g.internal/*/testdata/rapid/,test/testdata/rapid/), to confirm the pattern still matches at the intended depth. - If a pattern contains a middle slash (e.g. narrowing
testdata/totestdata/rapid/), know it anchors to the.gitignore's own directory and silently stops matching nested paths; use a leading**/form instead (e.g.**/testdata/rapid/) to keep matching at any depth. Never verify anchoring by reading the pattern alone. - In the real repo, write the proposed
.gitignoreand rungit status --porcelainto enumerate the full set of newly-untracked/visible files it exposes, then restore. - Stage only the explicit enumerated paths from that list — never
git add -Aorgit add .. - Confirm the staged set matches the enumerated list exactly by running
git diff --cached --name-only.
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.
- 28d ago First seen · 72 lines · 73 tokens per session scan A e25b6c38995c
gitignore-narrowing is a skill published in the GitHub repository toejough/engram (8 stars, last pushed yesterday), licensed Apache-2.0. It adds 73 tokens to every session and 1,002 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-21.
Other skills, from other repositories
meta-pre-commit-quality-gate
Run three quality gates (ruff + mypy + pytest) in parallel over the staged diff, then arbitrate a single BLOCK/APPROVE verdict. Use before committing changes locally when you want a comprehensive pre-commit gate beyond per-file linting — exactly the same gate set CI enforces.
commit
Create git commits with good messages. Use when user says "commit", "create commit", or asks to commit changes.
app_tagline_backfill
Give apps built on this instance a share-card tagline when their app.yaml has none. Runs automatically once after Rome upgrades (AUTO mode, list supplied by the caller) or on request from the guardian ("add taglines to my apps", MANUAL mode, confirm before writing). Only touches editable mode: "source" apps — never…
release
Cut a Memoria release. Version bump, CHANGELOG, CI workflows, Docker image. Use when publishing a new version.
commit
Generate git commit messages from staged changes.
knowledge-shell-process-and-worktree
Shell and Git worktree support for running commands, managing long-lived processes, and giving sessions isolated working directories. A Git worktree is a separate checkout linked to the same repository.