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/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/update-lid"><img src="https://agentmods.dev/badge/skills/jszmajda/lid/update-lid.svg" alt="Reviewed on agentmods" width="80" 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 | $0.04297 |
| Opus 5.5 | $0.00042 | $0.01719 |
| Sonnet 5.5 | $0.00021 | $0.00859 |
| Haiku 4.5 | $0.00011 | $0.00430 |
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 13d 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 — 182 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
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.
- 13d ago Changed · +11 lines c47475501afe
- 1mo ago First seen · 171 lines · 105 tokens per session scan A 17e786702888
update-lid is a skill published in the GitHub repository jszmajda/lid (115 stars, last pushed yesterday), licensed MIT. It adds 105 tokens to every session and 4,297 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
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…
add
Create a new Clawness rule from a natural language description. Describe what you want enforced and this will generate the YAML rule file with proper tags, triggers, and examples.
messaging
Write or rewrite the product's customer-facing copy — landing page, hero section, CTAs, onboarding, empty states, pricing, app-store and marketing pages — with the customer as the hero and the product as their guide. Scans the existing UI copy, drafts a one-page message brief (who the customer is, what they want, the…
review
Run an adversarial code review on staged changes or a specific file. Spawns the code-critic agent to find bugs, performance issues, and missed edge cases. Use before merging PRs or committing.
perf
Run a performance audit on the project or a specific module. Checks for N+1 queries, unnecessary re-renders, memory leaks, bundle size issues, and slow algorithms.
oneshot
End-to-end autonomous workflow — research, plan, implement, validate, ship, and merge in one command. ALWAYS use when the user says 'oneshot', 'do everything end to end', 'full workflow', or wants to go from ticket/idea to merged PR autonomously. All phases run sequentially in the current session, using agent teams…