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 hon454/grimoire --skill report-grimoire-issuegit clone --depth 1 https://github.com/hon454/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/hon454/grimoire/report-grimoire-issue)<a href="https://agentmods.dev/skills/hon454/grimoire/report-grimoire-issue"><img src="https://agentmods.dev/badge/skills/hon454/grimoire/report-grimoire-issue.svg" alt="Measured on agentmods" 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 | $0.00052 | $0.01015 |
| Opus 5 | $0.00026 | $0.00508 |
| Sonnet 5 | $0.00010 | $0.00203 |
| Haiku 4.5 | $0.00005 | $0.00102 |
Grade A, and why
report-grimoire-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 7d 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Report Grimoire Issue
Use this skill when the user wants to report a reusable problem, ambiguity, or improvement for Grimoire itself.
This is an explicit-invocation workflow. In Codex, invoke it as $report-grimoire-issue.
The upstream GitHub repository for issue search and posting is hon454/grimoire.
Goal
Turn a fuzzy Grimoire concern into a clean GitHub issue draft, then post it only after the user explicitly approves the exact title and body.
Scope
Use this skill for Grimoire-side changes:
- skills under
plugins/*/skills/ - plugin manifests and packaging metadata
- Codex harness behavior
- repository instructions and maintenance policy
- README or install guidance
- validation scripts, publishing checks, or issue templates
Do not use this skill for:
- one-off behavior that belongs only in the user's current project
- private repository prompt wording or domain-specific workflow preferences
- broad roadmap ideas without a concrete skill, plugin, documentation, or packaging change
- issues that would make Grimoire less generally reusable
Return MODE=local when the issue is project-local rather than Grimoire-side.
Interaction Rules
- Ask one question at a time when required information is missing.
- Prefer summarized reproductions over raw transcript excerpts.
- Never include secrets, private repository names, internal URLs, access tokens, customer data, or absolute local paths in the issue.
- Before presenting the final draft, sweep the title and body for private or project-local details.
- Never post an issue without first showing the exact draft and receiving explicit confirmation.
- If GitHub access is unavailable, return
MODE=draftwith the issue text for manual reuse.
Tool Use
Follow the using-grimoire
GitHub Operations rules.
When using gh, target hon454/grimoire explicitly.
Minimum Payload
Capture enough information to fill the Grimoire change-request issue shape:
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.
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.
- 7d ago First seen · 137 lines · 52 tokens per session scan A 2d0a1efe888d
report-grimoire-issue is a skill published in the GitHub repository hon454/grimoire (2 stars, last pushed 19d ago), licensed MIT. It adds 52 tokens to every session and 1,015 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 2026-08-31.
Other skills, from other repositories
dev-flow
Assess bounded Codex software development requests before choosing direct work or Dev Flow, then provision confirmed Dev Flow Tasks in dedicated Git worktrees. It may be selected implicitly or explicitly with $dev-flow-codex:dev-flow; the selector never skips assessment. Explicit Task resume and receipt-backed…
Tink: Setup
Configure Tink language, scope, git tracking, and policy.
package-update-check-and-plan
Read-only workflow for discovering uploaded deployment artifacts, comparing them with current deployment state, and preparing a safe update and rollback plan.
gstack-canary
GStack canary method for staged release thinking, smoke gates, rollout checks, and rollback signals before or after deployment.
gstack-document-release
GStack release documentation method for changelog, release notes, announcement copy, and internal/external release communication.
gstack-land-and-deploy
GStack land-and-deploy method for explicit landing and deployment workflows with tests, release notes, rollout gates, and rollback planning.