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/alexpialetski/doccraft/claude-mdgit clone --depth 1 https://github.com/alexpialetski/doccraftWrote 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/alexpialetski/doccraft/claude-md)<a href="https://agentmods.dev/instructions/alexpialetski/doccraft/claude-md"><img src="https://agentmods.dev/badge/instructions/alexpialetski/doccraft/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 | $0.01638 | $0.01638 |
| Opus 5 | $0.00819 | $0.00819 |
| Sonnet 5 | $0.00328 | $0.00328 |
| Haiku 4.5 | $0.00164 | $0.00164 |
Grade A, and why
doccraft 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Guidance for Claude Code agents working in this repo.
What doccraft is
An npm CLI that installs an opinionated, small set of docs-folder skills
for Claude Code and Cursor, layered on OpenSpec. On doccraft init,
doccraft first runs openspec init as a subprocess (installing OpenSpec's
own skills and slash commands), then installs its own skills on top.
Ships five core skills (authored in templates/skills/):
| Skill | Use for |
|---|---|
doccraft-story |
Product stories in docs/stories/ with typed YAML frontmatter |
doccraft-adr |
Architecture decision records in docs/adr/ (Nygard-style) |
doccraft-queue-audit |
Reconcile dependency graph + pick-next queue + backlog |
doccraft-session-wrap |
Propose doc artifacts at the end of a design thread |
doccraft-close |
Close a story end-to-end: status → backlog → queue → epic, then reconcile (ADR 015) |
Plus three Cursor rule stubs in templates/rules/ (planning-stories.mdc,
planning-adrs.mdc, planning-queue.mdc) that glob-attach when editing
the matching files under docs/.
This repo dogfoods its own skills
Everything under docs/ is authored using the installed skills
— the ADRs, stories, backlog, and queue are real planning artifacts, not
samples. The authoritative index lives in docs/README.md;
the Recently shipped section of docs/queue.md
summarises what's landed.
If you edit docs/stories/** or change depends_on values, invoke
doccraft-queue-audit to reconcile the tables — same workflow the
skill tells end users to follow.
Setup after cloning
Skills and rules are not committed (they are derivable from
templates/). Install them locally:
pnpm install
pnpm run dev:cli -- init . --skip-openspec --tools claude,cursor
That scaffolds doccraft.yaml if missing, writes
the four skills into .claude/skills/, and the three Cursor rule stubs
into .cursor/rules/. No dual-write — .cursor/skills/ is never
populated (ADR 007).
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 · 139 lines · 1,638 tokens per session scan A ecdf4e3890cf
doccraft CLAUDE.md is an instructions file published in the GitHub repository alexpialetski/doccraft (4 stars, last pushed 2mo ago), licensed MIT. It adds 1,638 tokens to every session, about $0.0082 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
cli CLAUDE.md
Claude Code instructions for archgate/cli, covering claude.md, technology stack, commands, validation gate and git hooks (git 2.54+).
llm-safe-haven CLAUDE.md
Claude Code instructions for pleasedodisturb/llm-safe-haven, covering llm safe haven, what this is, project structure, tdd — non-negotiable (adopted 2026-08-17) and the contract.
hiveshare CLAUDE.md
Instructions for KB-perByte/hiveshare, covering hiveshare — claude.md, repo layout, build & run, key env vars (server) and naming: hive vs memory.
kleosrules AGENTS.md
Instructions for kleosr/kleosrules, a project described as: Cursor harness pack: user rules, skills, Bash hooks, local HANDOFF memory. macOS, Linux, Windows (WSL).
finding-unknowns-skills CLAUDE.md
Claude Code instructions for Neeeophytee/finding-unknowns-skills, covering repo notes, what ships, and the gate that decides, version lives in three manifests — move them together, files that must be edited together and shipped guidance is not this file.
coding-agent-safety-gate AGENTS.md
Instructions for ASER-ho/coding-agent-safety-gate, covering agents / 代理规则, 仓库类型 / repository type and ai 代理规则 / rules for ai coding agents.