Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add ojCezarFerreira/Grimoire/plugin install 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/ojcezarferreira/grimoire/grimoire-init)<a href="https://agentmods.dev/skills/ojcezarferreira/grimoire/grimoire-init"><img src="https://agentmods.dev/badge/skills/ojcezarferreira/grimoire/grimoire-init/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/ojcezarferreira/grimoire/grimoire-init"><img src="https://agentmods.dev/badge/skills/ojcezarferreira/grimoire/grimoire-init.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 | $0.00023 | $0.01242 |
| Opus 5 | $0.00012 | $0.00621 |
| Sonnet 5 | $0.00005 | $0.00248 |
| Haiku 4.5 | $0.00002 | $0.00124 |
Grade A, and why
grimoire-init 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 9d 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
[Required Reading]
- Read
${CLAUDE_PLUGIN_ROOT}/GRIMOIRE-CONVENTIONS.md. Its rules (§ Skill composition, § .grimoire/ layout, § Project context, § Historic, § Commits, § IDE-aware review, § User-facing language, § Pause-point pattern) are load-bearing for this skill. - If
.grimoire/HISTORIC.mdexists, read it for recent-page context (older context lives in.grimoire/bag/historic/, newest suffix first). Missing → proceed without it; do not create it (bootstrap is owned bygrimoire-spec, not this skill).
[Objective]
Build a shared understanding of the current project — what it is, who it's for, how it's built — and persist it as .grimoire/PROJECT.md. From then on every other Grimoire skill loads that file on startup as project context.
Optional extra context or focus areas from the user:
$ARGUMENTS
[Phase 1: Mode Detection & Codebase Analysis]
- Check whether
.grimoire/PROJECT.mdalready exists in the project root.- If it exists: read it first. This run is an UPDATE — preserve everything still accurate and only revise what has changed or is missing.
- If it does not exist: this run is an INITIALIZATION — start from scratch.
- Scan the project for signals. Read only what is needed to form an opinion:
- README files at the root.
- Package manifests (
package.json,pyproject.toml,Cargo.toml,go.mod,Gemfile,composer.json, etc.). - Build / language config (
tsconfig.json,vite.config.*,next.config.*,pnpm-workspace.yaml, etc.). - CI/CD definitions under
.github/workflows/,.gitlab-ci.yml, etc. - Top-level directory layout (one level deep).
LICENSE,CONTRIBUTING.md,CODE_OF_CONDUCT.mdif present.
- Collect candidate facts: project name, primary languages / frameworks, notable dependencies, build & test commands, repository layout, audience hints. Do not invent facts — anything you cannot infer goes into Phase 2 as a question.
[Phase 2: Clarifying Questions]
Per § Pause-point pattern (grimoire-init: clarifying questions), ask the user concise, targeted questions about ONLY what cannot be inferred from the codebase. Typical topics:
- The project's purpose — what problem it solves.
- The intended audience or users.
- The current stage (prototype / active development / production / maintenance).
- Non-obvious conventions, constraints, or invariants a new contributor should know.
- Anything to deliberately exclude from
PROJECT.md.
In UPDATE mode, ask only about deltas — what has changed since the existing PROJECT.md was written, and whether any section is now stale.
In UPDATE mode, when ## Key Conventions / Constraints and/or ## Notes in the existing PROJECT.md already contain one or more entries, list those entries back to the user briefly (slug or first ~10 words per bullet) and ask "Anything stale here?". Default action is preserve in place — only remove or rewrite a specific entry when the user gives an explicit delta. Silence means keep everything. The user may still add new entries via this Phase 2 interview, exactly as before. Per § Project context's dual-writer contract, these two sections are also owned by grimoire-note, so init's default is preserve-in-place. The full-rewrite/refresh behavior of update mode is unchanged for ## Purpose, ## Audience, ## Tech Stack, ## Repository Layout, and ## Current Status — only these two sections get preserve-by-default protection.
Wait for the user's answers before drafting PROJECT.md.
[Phase 3: Draft Review]
-
Compose the proposed
PROJECT.mdusing this template:# <Project Name> ## Purpose ## Audience ## Tech Stack ## Repository Layout ## Key Conventions / Constraints ## Current Status ## Notes -
Present the proposed content for review per
§ IDE-aware review:- IDE detected: create
.grimoire/in the project root if it does not exist, then write the draft to.grimoire/PROJECT.mdso the IDE renders it. Tell the user in one short line that the draft is open in the editor. - Terminal-only fallback: output the proposed content inline in the chat.
- IDE detected: create
-
Pause per
§ Pause-point pattern(grimoire-init: draft review): wait for the user's confirmation or edits. Do not advance to Phase 4 until approved. If the user abandons the draft, delete the file (IDE mode 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.
- 9d ago First seen · 74 lines · 23 tokens per session scan A fb5dbe57a9db
grimoire-init is a skill published in the GitHub repository ojCezarFerreira/Grimoire (2 stars, last pushed 2mo ago), licensed MIT. It adds 23 tokens to every session and 1,242 once invoked, about $0.0001 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
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
story-readiness
Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…
autotask-creator
Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.
projects
List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.