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 Jartan-LLC/grimoire --skill implement-issuegit clone --depth 1 https://github.com/Jartan-LLC/grimoireWrote 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/jartan-llc/grimoire/implement-issue)<a href="https://agentmods.dev/skills/jartan-llc/grimoire/implement-issue"><img src="https://agentmods.dev/badge/skills/jartan-llc/grimoire/implement-issue/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/jartan-llc/grimoire/implement-issue"><img src="https://agentmods.dev/badge/skills/jartan-llc/grimoire/implement-issue.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 | $0.00015 | $0.00723 |
| Opus 5.5 | $0.00006 | $0.00289 |
| Sonnet 5.5 | $0.00003 | $0.00145 |
| Haiku 4.5 | $0.00002 | $0.00072 |
Grade A, and why
implement-issue 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 4d 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implement Issue
Implement changes for a GitHub issue.
Where the project's own rules say otherwise, follow them.
Process
1. Load Context
Determine the issue number from the user's request, which may carry context beyond the number. Fetch the issue and any plan comments:
gh issue view <issue-number> --comments
Also check .claude/workspace/ for any plan files related to this issue. If no plan exists for a complex issue, suggest running /praxis:plan-issue first.
2. Setup Branch
Load the gitwise:github-conventions skill. Check existing local and remote branches for one related to this issue -- it may be named by issue number (feature/issue-123) or by description (feature/audit-improvements). If one exists, check it out. If not, create a new branch. For sub-issues of a larger feature, branch from the parent feature branch rather than main.
3. Read Relevant Docs
Based on the issue area, read the appropriate project documentation in docs/.
4. Implement
Load the gitwise:commit-pr-writing skill. Follow the plan if one exists. Work through changes methodically. Make progressive commits as logical units of work are completed rather than one monolithic commit at the end, writing each commit message as gitwise:commit-pr-writing says.
5. Update Documentation
Load the praxis:docs-patterns skill. Before you edit any README, CONTRIBUTING.md, release procedure, changelog or agent instruction file, read that document's file in docs-patterns (readme.md, contributing.md, releasing.md, changelog.md, agent-files.md), even when the skill is already loaded. Search every README and agent instruction file (CLAUDE.md, AGENTS.md, the files they import or name as the rules, .claude/rules/, other tools' equivalents) for each command, option, setting, default, path, make target or skill the change adds, renames, removes or alters. Update CONTRIBUTING.md when the change alters setup, the check, a convention or what a change owes. Update the release procedure when the change touches how the project releases (a release workflow, tag pattern, publish job or version rule). Where the project keeps a changelog, add the entry the change owes. Commit doc 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.
- 4d ago Changed c81e230e1ce4
- 5d ago Changed · -1 lines a1901f17f2c4
- 1mo ago First seen · 63 lines · 15 tokens per session scan A 76bfb4ab6041
implement-issue is a skill published in the GitHub repository Jartan-LLC/grimoire (2 stars, last pushed yesterday), licensed MIT. It adds 15 tokens to every session and 723 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
ship
Prepare or execute an authorized controlled release with verified checks, recovery and an operating owner. Use when a customer increment is ready for deployment.
log-changes
Use before creating, drafting, editing, or reviewing changelog entries (CHANGELOG.md or the project's equivalent), including when this is a subtask of implementing a feature, fixing a bug, or preparing a release and the user did not explicitly ask for this skill. Also use for requests to 'document this change' or 'add…
create-pr
Use when asked to create a pull request, open a PR, or submit changes for review. Handles branch verification, change analysis, title and description generation, and gh pr create. Do NOT use for committing, pushing without PR, or reviewing existing PRs.
check-dependabot
Validate a Dependabot configuration against the published JSON Schema and audit its groups against the repository's real dependency manifests. Use when creating or rewriting .github/dependabot.yml, when adding or reorganising groups, ignore or exclude-patterns, when a dependency lands in the wrong grouped PR or keeps…
monitor-ci
Drive a long-running GitHub Actions run to a trustworthy conclusion without burning the session on polling. Use when asked to wait for a pipeline, watch a build, babysit a release or deploy run, restart it if it fails, or report whether it went green. Also use when a run must finish before a follow-up step such as a…
git-commit
Use when asked to commit, save, or persist changes to Git. Handles atomic commits, branch safety, Conventional Commits format, and project style matching. Do NOT use for pushing, creating PRs, or branch management beyond safety checks.