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 jszmajda/lid --skill lid-coachgit clone --depth 1 https://github.com/jszmajda/lidWrote 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/jszmajda/lid/lid-coach)<a href="https://agentmods.dev/skills/jszmajda/lid/lid-coach"><img src="https://agentmods.dev/badge/skills/jszmajda/lid/lid-coach/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/jszmajda/lid/lid-coach"><img src="https://agentmods.dev/badge/skills/jszmajda/lid/lid-coach.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 | $0.00117 | $0.11415 |
| Opus 5 | $0.00059 | $0.05708 |
| Sonnet 5 | $0.00023 | $0.02283 |
| Haiku 4.5 | $0.00012 | $0.01141 |
Grade B, and why
lid-coach scanned grade B with 1 finding 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 10d 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.
Strips warnings and disclaimersmediumAnti-refusal
Omitting safety caveats hides risk from the user and is a common jailbreak preamble.
The knowledge base for these conversations lives in `references/lid-faq.md`. **Load that file on demand** when the user's prompt looks like an adoption / pattern / how-do-I question, draw on its framings, and answer in y How it starts
The opening of the file, as written. The whole thing — 342 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LID Coach
Reviews a project's current LID usage against LID's own principles and produces a prioritized set of recommendations. The posture is advisory: the project works; this skill tells the user where patterns are drifting from LID's principles or leaving value on the table.
This skill is invoked only by the /lid-coach command. It does not auto-trigger — a principle review reads a broad slice of the project and would be wasteful to fire opportunistically.
What this skill is not
- Not a configuration reconciler. That is
/update-lid. When a finding implies a configuration change, point the user there. - Not a structural auditor. That is
/arrow-maintenance(when the overlay is installed). When a finding is structural in nature — orphans, reverse orphans, adjacent-level coherence,index.yamldrift — surface the pattern and recommend/arrow-maintenancefor the precise enumeration. Do not attempt to enumerate structural instances from sampled reads. - Not a file editor. Advisory posture is load-bearing. Produce the report; the user applies.
Dispatch
On invocation, inspect the project and take exactly one of these actions:
| Detected state | Action |
|---|---|
No instruction file (the project's AGENTS.md, or CLAUDE.md under Claude Code) and no LID-shaped artifacts anywhere in the project (no HLD, no LLDs, no specs, no arrow overlay) |
Inform the user the project is not LID-configured; recommend /update-lid. Do not proceed with coaching. |
| The instruction file absent or missing LID directives but the project has LID-shaped artifacts (see threshold below) | Proceed with a full review anchored on the existing artifacts (default Full mode). Surface the missing (or precursor-named) instruction-file directives as a high-priority finding recommending /update-lid to reconcile. Do not refuse — a project with a populated arrow is LID-shaped regardless of whether the instruction file has caught up with the directive naming. |
LID directives present, but docs/intent/ or docs/high-level-design.md is missing |
Proceed with a reduced review of what exists. Surface each missing piece as a high-priority finding and recommend /update-lid to reconcile. |
Scoped mode with missing or empty ## LID Scope |
Surface the misconfiguration as a high-priority finding. Run a conservative project-wide review treating all paths as in-scope. |
docs/arrows/index.yaml present but cannot be parsed |
Flag corruption to the user before any principle review. Offer either to proceed with a reduced review treating the overlay as absent, or to pause for the user to repair. |
| Fully configured (directives + mode marker + standard directories; Scoped with valid scope) | Proceed with a full review. |
What ships with it
2 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.
- 10d ago First seen · 342 lines · 117 tokens per session scan B 1096618f9b73
lid-coach is a skill published in the GitHub repository jszmajda/lid (101 stars, last pushed 28d ago), licensed MIT. It adds 117 tokens to every session and 11,415 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it B with 1 finding (strips warnings and disclaimers). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
bootstrap
Author a starter set of Clawness rules for a project whose stack Clawness ships no corpus for (Ruby, PHP, Elixir, Haskell, C#, Swift, Dart, Scala, Clojure, ...). Researches the stack's current conventions from official documentation, drafts a small set of project rules into .clawness/rules/, lint-validates them, and…
refresh
Bring this project's Clawness rules up to date with the framework version it actually runs. Establishes what is installed and what the codebase uses, looks up what changed since the rules were verified, and writes version-corrected overrides into .clawness/rules/ — reporting the list and stopping for approval before…
user-docs
Write user documentation for a project by scanning its codebase — its UI screens and its public API/CLI — inferring what someone can actually do with it, and drafting brief, task-oriented docs to the Diátaxis standard (tutorial / how-to / reference / explanation). Handles both non-technical end-user docs and developer…
audit-rules
Review one domain of the Clawness rule corpus for correctness against current official documentation, then record what was established as a version stamp (appliesto / verified / sources) on each rule individually. For maintainers and fork maintainers. Reports verdicts and writes stamps; never rewrites rule text.
eval-set
Build and run a project-specific retrieval eval so changes to your rules or base prompt are scored, not eyeballed. Mirrors tests/groundtruth.json + clawness eval: you write prompt→expected-rule cases, then measure MRR@k and hit-rate before and after an edit. Run it after trimming a base prompt into ranked retrieval…
security-audit
Run a stateful red team / blue team security audit on the current project or a specific module. First enumerates the attack surface deterministically with clawness scan (zero LLM tokens, identical every run) and accumulates verdicts in a findings ledger, so each pass adjudicates only what is NEW instead of re-scanning…