Borrowing it
Nothing to install: this file belongs to jfarcand/mirroir-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/jfarcand/mirroir-mcp/main/.claude/skills/bilan/SKILL.mdgit clone --depth 1 https://github.com/jfarcand/mirroir-mcpWrote 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/jfarcand/mirroir-mcp/bilan)<a href="https://agentmods.dev/skills/jfarcand/mirroir-mcp/bilan"><img src="https://agentmods.dev/badge/skills/jfarcand/mirroir-mcp/bilan/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/jfarcand/mirroir-mcp/bilan"><img src="https://agentmods.dev/badge/skills/jfarcand/mirroir-mcp/bilan.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 | $0.00069 | $0.03128 |
| Opus 5.5 | $0.00028 | $0.01251 |
| Sonnet 5.5 | $0.00014 | $0.00626 |
| Haiku 4.5 | $0.00007 | $0.00313 |
Grade A, and why
bilan 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 29d 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 — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bilan
The completion number is this script's number, never yours.
The incident history quoted below (carnet#236, carnet#406, carnet#493, …) happened in the
dravr-* family, where this skill was built; those numbers are in dravr-ai/dravr-carnet, not in
this repo's register.
It used to be narrated: it came from my account of the session, so a session that believed it
was done reported 8 or 10 while it still held open carnet issues, had commits sitting unpushed,
or had left a background task running. Every one of those facts is machine-checkable, and
bilan.sh checks them.
.claude/skills/bilan/bilan.sh # full: local facts + one CI query
.claude/skills/bilan/bilan.sh --cheap # local only, no network
.claude/skills/bilan/bilan.sh sweep # what a session that DIED left behind
Exit code: 0 = 10/10 · 1 = incomplete · 2 = the script itself failed.
--cheap and the full run give the same number. CI is printed, never scored (below), so
skipping it changes what is shown, not the score — and every other check answers from local
evidence in both modes. --cheap is the form a hook or a status line runs, which is why that
has to hold: a check that only the full run can pass would hold every cheap reading below it for
as long as the condition stands.
The rules
- Run it before you give a number. Report the score it prints. If you believe a cap is wrong, say so in words and still report the script's number — arguing with the measurement is a conversation, overriding it silently is the failure this exists to stop.
- A cap is a fact, not an opinion. Each one prints its own evidence and its own remedy.
The score is
min()over the caps, so one open carnet issue holds the whole session at 6 no matter how much else landed. - Failures never deduct. A red that is now green, a mistake found and fixed, a rough path — none of it lowers the number. The score measures completion, and only completion.
- Friction is printed, never scored. Tool errors, interrupts and denials are counted from the transcript and shown for context. They do not cap anything.
What ships with it
3 files 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.
- 29d ago First seen · 211 lines · 69 tokens per session scan A ddbd31564d10
bilan is a skill published in the GitHub repository jfarcand/mirroir-mcp (265 stars, last pushed 2d ago), licensed Apache-2.0. It adds 69 tokens to every session and 3,128 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 2026-09-24.
Other skills, from other repositories
skill
Capture and transcribe meeting audio, optionally with screen content, and manage the meeting library. Commands: start | stop | status | watch | writeup | list | show | search | delete | doctor.
macbeth
How to drive macOS apps with Macbeth MCP tools — discovery, locators, actions, menus, screenshots/OCR, handles, and fallbacks.
messages
Browse conversations, read messages, and send texts in Apple Messages.
safari
Navigate, search, click links, read content, and manage tabs in Safari.
electron
Automate Electron apps (Slack, VS Code, Discord, etc.) whose UI is Chromium web content exposed through the Accessibility API.
logicpro
AX-first automation for Logic Pro — transport, tracks, tempo, mixer, and view controls.