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/register-limitation/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/register-limitation)<a href="https://agentmods.dev/skills/jfarcand/mirroir-mcp/register-limitation"><img src="https://agentmods.dev/badge/skills/jfarcand/mirroir-mcp/register-limitation/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/register-limitation"><img src="https://agentmods.dev/badge/skills/jfarcand/mirroir-mcp/register-limitation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00060 | $0.01182 |
| Opus 5 | $0.00030 | $0.00591 |
| Sonnet 5 | $0.00012 | $0.00236 |
| Haiku 4.5 | $0.00006 | $0.00118 |
Grade A, and why
register-limitation 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 11d 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Register a Limitation
When this fires
Any of these, without exception:
- The register gates failed — "unregistered deferral/confession prose", "malformed LIMITATION marker", a file over the 500-line cap, or an inline clippy allow outside the declared list.
- You are about to write a comment explaining why something is incomplete, restricted, or deferred.
- You are shipping a feature disarmed (flag off, shadow mode, log-only phase).
- You found a gap while reading code and are not fixing it in this change.
The gates are the Apache-2.0 llm-registre tool,
vendored as the .registre submodule and run by Tier 1 of
runner/scripts/ci/pre-push-validate.sh and by CI (limitation-register.yml).
Step 0 — try to not need this
The register exists so honest gaps become tracked obligations, not so gaps become easy to ship. If you can implement the real thing now, do that instead. Registering is the fallback, and it costs a permanent entry someone has to close later. (A file over the cap or a stray inline allow is never registered — extract the helper or fix the lint.)
Where issues go
Read registre.toml at the repo root — its tracker key names this repo's register. Never
assume; registers are per project. For mirroir that is jfarcand/mirroir-carnet.
grep tracker registre.toml
| Tracker | whatever registre.toml says |
| Labels | limitation + this repo's name (iphone-mirroir-mcp) |
| Title | [mirroir-mcp] <short statement of the gap> — always project-prefixed |
Never file on the code repo itself. It is PUBLIC, and a limitation issue states precisely where a capability or defence is incomplete — a roadmap when the code is open. Issue bodies may hold reasoning and residual risk; the code comment stays thin.
Step 1 — file the issue
TRACKER=$(sed -n 's/^tracker[[:space:]]*=[[:space:]]*"\(.*\)"/\1/p' registre.toml)
gh issue create -R "$TRACKER" \
--title "[mirroir-mcp] Short statement of the gap" \
--label limitation --label iphone-mirroir-mcp \
--body "Where it is (file + symbol). What is incomplete. What the correct fix looks like."
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.
- 11d ago First seen · 115 lines · 60 tokens per session scan A 987e0321b099
register-limitation is a skill published in the GitHub repository jfarcand/mirroir-mcp (214 stars, last pushed 2d ago), licensed Apache-2.0. It adds 60 tokens to every session and 1,182 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 2026-08-30.
Other skills, from other repositories
daily-briefing
Start your day with a prioritized CRM briefing — works for any monday CRM setup: pipeline, contacts, accounts, leads, or no board at all. Use when someone says 'morning briefing', 'daily brief', 'what's on my plate today', 'catch me up on my deals', 'what needs attention', 'what needs my attention', 'anything urgent…
meeting-to-deal
Turn meeting transcripts into deal updates — key points, commitments, and next steps posted to matching CRM deals automatically. Auto-creates contacts for new attendees. Use when someone says "log my meetings to deals", "update CRM from calls", "what did I commit to in meetings", "sync notetaker", "log this meeting"…
task-workstream-grouping
Infer stable semantic workstreams for ungrouped Sutando task history and apply the validated assignments to the durable workstream sidecar. Use for internal task-workstream-grouping maintenance tasks, initial history backfills, and later batches of tasks that need cross-channel or cross-device workstream organization.
Technical Debt Tracking with PMAT
Tracks and manages technical debt using PMAT (Pragmatic AI Labs MCP Agent Toolkit). Use this skill when: User asks about technical debt, TODO comments, or code quality issues Planning sprint work and need to prioritize debt repayment Conducting code audits or technical debt assessments Tracking debt accumulation…
autopilot
Carry a well-scoped GitHub issue through the full dev loop autonomously, stopping at a per-run tier boundary (PR-ready, or merge+deploy for small reversible changes).
autopilot-triage
Vet open issues for autonomous resolution and queue the qualifying ones with the autopilot-queued label — the start-of-day "fill the queue" half of the triage → run split.