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 yannlugrin/claude --skill index-projectgit clone --depth 1 https://github.com/yannlugrin/claudeWrote 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/yannlugrin/claude/index-project)<a href="https://agentmods.dev/skills/yannlugrin/claude/index-project"><img src="https://agentmods.dev/badge/skills/yannlugrin/claude/index-project/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/yannlugrin/claude/index-project"><img src="https://agentmods.dev/badge/skills/yannlugrin/claude/index-project.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 | $0.00107 | $0.01908 |
| Opus 5 | $0.00053 | $0.00954 |
| Sonnet 5 | $0.00021 | $0.00382 |
| Haiku 4.5 | $0.00011 | $0.00191 |
Grade A, and why
index-project 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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Index this project
The catalog gives every future session a one-line awareness of the user's other projects: what exists, what it is for, where it lives. This skill is the write path — and it exists because the entry has to be written by a session that has the project already loaded. Nobody else can say in one line what a repository is for.
The read path is the SessionStart hook and its show command; you do not
touch those here.
What you are writing
Only what cannot be derived. Descriptions, commits and branch state are read
live by show, so never copy a README into the catalog — a copy drifts, the
original does not.
| field | what it holds |
|---|---|
name |
how the user refers to the project in conversation — distinct on its own, since the index shows it without its path |
path |
where the working copy lives |
repo |
owner/name on the forge, if there is one |
role |
one line, ≤ 80 characters, what the project is for |
status |
planned | active | paused | archived |
visibility |
private (default) | public |
part_of |
the family this project belongs to, if it is one of several |
relates_to |
other catalogued name → the reason it matters |
Steps
0. A name is not the directory name. A working copy is named for
convenience on disk — a short word inside a container directory — while a
catalog entry is read on its own, beside every other project. tools under
~/projects/claude/ is unambiguous in a shell and says nothing in an index.
Ask what the user calls the project when talking about it. Renaming later is
project-catalog.py rename <old> <new>, which also fixes every relation
pointing at the old name; never rename by editing the file.
1. Check for an existing entry. Run ~/.claude/hooks/project-catalog.py show <name>, and list to see the names already in use. Re-running this
skill in an already-listed project updates that entry; it never adds a second
one. An existing entry is a draft to correct, not a blank page.
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 · 141 lines · 107 tokens per session scan A ed3a577c2d57
index-project is a skill published in the GitHub repository yannlugrin/claude (2 stars, last pushed 13d ago), licensed MIT. It adds 107 tokens to every session and 1,908 once invoked, about $0.0005 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.