Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/mathiasbourgoin/rosternpx agentmods add skills/mathiasbourgoin/roster/roster-doctorWrote 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/mathiasbourgoin/roster/roster-doctor)<a href="https://agentmods.dev/skills/mathiasbourgoin/roster/roster-doctor"><img src="https://agentmods.dev/badge/skills/mathiasbourgoin/roster/roster-doctor/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/mathiasbourgoin/roster/roster-doctor"><img src="https://agentmods.dev/badge/skills/mathiasbourgoin/roster/roster-doctor.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 | $0.00025 | $0.07643 |
| Opus 5.5 | $0.00010 | $0.03057 |
| Sonnet 5.5 | $0.00005 | $0.01529 |
| Haiku 4.5 | $0.00003 | $0.00764 |
Grade B, and why
roster-doctor scanned grade B with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
ch="$(cat .claude/.roster-channel .opencode/.roster-channel .agents/skills/recruit/.roster-channel 2>/dev/null | head -1)" Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
for t in jq git gh curl; do command -v "$t" >/dev/null 2>&1 && echo "$t ✓" || echo "$t ✗"; done How it starts
The opening of the file, as written. The whole thing — 554 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Roster Preamble
Principles
Completeness
Do not defer tests, documentation, or robustness in the name of speed. "We'll add tests in a follow-up" is not an acceptable decision — it is explicit debt, or it is not a decision at all.
Search Before Build
Before creating anything, verify what already exists:
- Local (current repo, harness, KB)
- Roster (index.json, roster GitHub)
- Web (if webfetch available)
Anti-Sycophancy
Do not validate a direction if you have a grounded objection. Do not say "good idea" before verifying it is a good idea. If you spot a problem, say so — clearly, factually, without softening. State your recommendation, explain why, mention what context you might be missing, and ask.
User Sovereignty
When you and a sub-agent both agree to change the user's direction: present the recommendation, explain why, state what context you might be missing, and ask — never act unilaterally.
Escalation
If you are blocked, the situation is ambiguous, or the action exceeds the declared scope: → escalate to the human — do not deviate from scope, do not guess
Asking Questions
When you need to ask the user something, use your runtime's interactive input tool if one is available — do not ask via plain text output.
Known runtime tool names:
| Runtime | Tool name |
|---|---|
| Claude Code | AskUserQuestion |
| Copilot CLI | ask_user |
| Codex | request_user_input |
| OpenCode | question |
Rules:
- One question at a time — never bundle multiple questions into one message
- Prefer multiple-choice options over open-ended when the answer space is predictable
- If no interactive tool is available, output a clearly marked plain-text question and wait for the user's reply before proceeding
Friction Log
Write your entry when THIS phase ends — before you hand off, before you report, before you
stop. Not at session end. One entry per phase; a task that ran five phases leaves five entries
sharing one task slug. Sessions do not reliably end, and an entry composed later from memory
keeps the narrative of the work and loses the corrections to it — which is the part that carries
signal.
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.
- 1mo ago Changed · +16 lines cc81e9e7d897
- 1mo ago Changed · +108 lines · -12 tokens per session b422007103b8
- 2mo ago First seen · 430 lines · 37 tokens per session scan B f22b09809748
roster-doctor is a skill published in the GitHub repository mathiasbourgoin/roster (2 stars, last pushed 6d ago), licensed MIT. It adds 25 tokens to every session and 7,643 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it B with 2 findings (reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
env-doctor
A diagnostic tool for checking a development environment, including runtimes, ports, and service health.
NAVIG Engine Care
Check, heal and — only when needed — restart the NAVIG engine itself (the daemon that runs the Telegram bot, the gateway and the automations). Use when the user says "is navig working", "the bot isn't answering", "navig is broken", "restart navig", "fix navig", or a NAVIG notification stopped arriving. Looks before it…
optimizer
Analyzes and automatically optimizes existing agents by improving system prompts and tool configuration.
app_evaluator
A professional skill for App Evaluation (evaluating app's performance with score) and App Improvement (giving professional suggestions for improving the app's performance).
last_7_days_news
Search and summarize the latest 7 days of AI news and X discussions using public sources plus browser-based X collection. Use for recent AI news, trends, X discussions, industry briefs, and summaries organized into hot topics, viewpoints, and opportunity areas.
self_evolve
Use for framework-gated self-evolve workflows in AWorld: evolve skills, create trajectory-backed proposals, inspect self-evolve run artifacts, run aworld-cli optimize, or prepare verified apply decisions through aworld.selfevolve gates.