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 agentmods add instructions/progiri/craftlight/claude-mdgit clone --depth 1 https://github.com/progiri/craftlightWrote 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/instructions/progiri/craftlight/claude-md)<a href="https://agentmods.dev/instructions/progiri/craftlight/claude-md"><img src="https://agentmods.dev/badge/instructions/progiri/craftlight/claude-md.svg" alt="Measured on agentmods" 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 | $0.00743 | $0.00743 |
| Opus 5 | $0.00371 | $0.00371 |
| Sonnet 5 | $0.00149 | $0.00149 |
| Haiku 4.5 | $0.00074 | $0.00074 |
Grade A, and why
craftlight CLAUDE.md 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 4d 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 — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — craftlight
A marketplace repository with the craftlight plugin (seven skills of one discipline). Here the skills are
developed, not applied to a third-party project.
Structure
.claude-plugin/marketplace.json— the marketplace manifest.plugins/craftlight/.claude-plugin/plugin.json— the plugin manifest (version).plugins/craftlight/skills/{task,plan,wave,brief,debug,code-review,craft-graph}/— skills:SKILL.md+tests/(+templates/where the skill owns an artifact,modes/for the multi-mode ones).docs/crafts/<slug>/{BRIEF,SPEC,PLAN}.md— briefs, tasks, and plans of initiatives (in-progress and completed);docs/crafts/_backlog.md— the "noticed along the way" sink;docs/graph/— the plugin's decision graph (seeCRAFT.md).
How to "test"
There are no automated tests. After ANY edit to SKILL.md / modes/* / templates/*, run this skill's regression
scenarios (skills/<skill>/tests/scenarios.md): parallel read-only sonnet-level subagents, each given its prompt
without the "Expected" block; the agent decides and cites the rule; compare against "Expected".
Update the "Last run" line. Validate manifest JSON (python3 -c "import json; json.load(open('...'))").
Start
Begin understanding the project from CRAFT.md, then docs/graph/_overview.md.
craftlight
The discipline of this repository (the craftlight plugin):
- Changing code → the
taskskill (modes S/M/L; risk zone — auth/secrets, money, migrations & data deletion, PII, concurrency invariants, external API contracts — minimum M). - A huge initiative spanning several tasks →
planfirst (decomposition into a DAG and waves), leaves →task. - A plan's wave, run in parallel →
wave(one gate over the wave; leaves in worktrees; the wave lands as one PR). - Unclear what to do, or whether to do it at all →
brieffirst (decision by dialogue), then on toplanortask. - Review without edits →
code-review. Decisions and gotchas as a graph →craft-graph. - Start understanding the project from
CRAFT.md, thendocs/graph/; the project's glossary — the rootCONTEXT.md: use its terms in speech, code, and artifacts. docs/crafts/*/{BRIEF,SPEC,PLAN,DEBUG}.mdwith statusin-progressordraft= an active artifact: offer to resume (a draft resumes at its gate, not into execution) — a new task isn't blocked by it.- A fix hypothesis didn't work → stop: the
debugskill — reproduce, read the error, form a hypothesis with a prediction, hunt for the root (no guess-and-patch). Diagnosis without a fix; the cure istask. craftlight:lines in context are advisory hook hints: they recall the rules, they don't replace a playbook or grant permissions.
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.
- 4d ago First seen · 40 lines · 743 tokens per session scan A 3ee2ccf918da
craftlight CLAUDE.md is an instructions file published in the GitHub repository progiri/craftlight (5 stars, last pushed 10d ago), licensed MIT. It adds 743 tokens to every session, about $0.0037 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 2026-08-31.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.