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 update-lidgit 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/update-lid)<a href="https://agentmods.dev/skills/jszmajda/lid/update-lid"><img src="https://agentmods.dev/badge/skills/jszmajda/lid/update-lid.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Memory Poisoning · line 164 Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.Fix: Protect agent memory and state from modification by untrusted content. Use read-only memory for critical instructions and validate all state changes.
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 | $0.00105 | $0.03767 |
| Opus 5 | $0.00053 | $0.01884 |
| Sonnet 5 | $0.00021 | $0.00753 |
| Haiku 4.5 | $0.00011 | $0.00377 |
Grade A, and why
update-lid 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 8d 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 — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
update-lid
Configure or reconcile a project for linked-intent development. Dispatches on project state — do not re-run unconditionally.
Invoked as /update-lid. The skill handles both initial bootstrap and ongoing reconciliation; the user's mental model differs ("set me up" vs. "update what we have") but the behavior dispatches on what's detected in the project, not on the user's framing.
Instruction-file anchor
LID's directives, the ## LID block, and the navigation table live in the project's agent-instructions file. Canonically that is AGENTS.md (the cross-tool convention Cursor and most agents read), with CLAUDE.md a symlink alias so Claude Code sees the same content. Never branch on which host you are running under.
- Read (detect directives, mode, version, drift): use
AGENTS.mdif it exists, otherwiseCLAUDE.md. With the symlink the two are one file. - Fresh bootstrap (write): create
AGENTS.mdand aCLAUDE.mdsymlink pointing at it (ln -s AGENTS.md CLAUDE.md). Where symlinks are unavailable (e.g. Windows without Developer Mode), instead write aCLAUDE.mdwhose only content is@AGENTS.md. - Existing project (write): update the file that already exists, in place. A project that already uses
CLAUDE.mdkeeps it — do not migrate it toAGENTS.md.
Below, the instruction file means the file chosen by these rules.
Detection signals
Use these exact detection rules — do not guess or use fuzzy matching.
- LID directives present:
grepfor the literal strings"linked-intent-dev"or"Linked-Intent Development"in the instruction file. Either match indicates LID directives are already installed. - LID metadata block present:
grepfor a## LIDheading in the instruction file. The block carries two bullets:- Mode: {Full|Scoped}— the project's LID mode. Case-insensitive on the mode name; whitespace tolerated.- Version: {X.Y.Z}— thelinked-intent-devplugin version the project's docs conform to. A project with a## LIDblock but no- Version:bullet is treated as predating versioned conventions (no- Version:bullet) (walk from the start).
- Project version vs. installed version: read
- Version:from the## LIDblock and compare it to the installedlinked-intent-devplugin version (theversionfield inplugins/linked-intent-dev/.claude-plugin/plugin.json, the canonical LID conventions version). When the project version is lower, the project lags and version-walk applies. - Arrow-maintenance overlay present:
docs/arrows/directory exists at the project root. - Convention drift: any of the required directories missing (
docs/intent/,docs/high-level-design.md); the instruction-file directive sections diverge from the current template, including a malformed## LIDblock (heading other than a bare## LID, mode merged into the heading as## LID Mode: Full, a missing- Mode:or- Version:bullet, or stray non-template bullets); a design doc whoseprefix:frontmatter is an array (an unresolved multi-prefix marker — see Version-walk); or a node folder holding more than its<node>-design.md+ optional<node>-specs.mdpair (an un-promoted sub-LLD left as extra files). The last two are detected independently of version lag — a project already at the installed version still has them re-surfaced by reconcile-conventions, and handled the same way (surfaced with a recommended resolution, never silently left or auto-resolved).
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.
- 8d ago First seen · 171 lines · 105 tokens per session scan A 17e786702888
update-lid is a skill published in the GitHub repository jszmajda/lid (101 stars, last pushed 26d ago), licensed MIT. It adds 105 tokens to every session and 3,767 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 2026-08-30.
Other skills, from other repositories
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…
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…
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…
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.
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…