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.
git clone --depth 1 https://github.com/hamr0/agentic-toolkitWrote 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/commands/hamr0/agentic-toolkit/docs-builder)<a href="https://agentmods.dev/commands/hamr0/agentic-toolkit/docs-builder"><img src="https://agentmods.dev/badge/commands/hamr0/agentic-toolkit/docs-builder/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/commands/hamr0/agentic-toolkit/docs-builder"><img src="https://agentmods.dev/badge/commands/hamr0/agentic-toolkit/docs-builder.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 | $0.00020 | $0.04320 |
| Opus 5.5 | $0.00008 | $0.01728 |
| Sonnet 5.5 | $0.00004 | $0.00864 |
| Haiku 4.5 | $0.00002 | $0.00432 |
Grade A, and why
docs-builder 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 11d 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.
This is a copy
100% identical to docs-builder — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.
docs-builder
Keep project docs current, complete and findable, and split a file when it outgrows its row in docs/index.md. Why it works this way, measured numbers and history: docs/product/docs-builder-README.md.
This does NOT make docs cheaper to read — never sell it as a token saving. Every mechanical step is the docs-builder.cjs script beside this file, the $DB path below (vanilla Node, zero deps). A model does two things only: classify and propose themes, and write pages.
- Heavy model work always spawns a worker, tier stated explicitly (an omitted tier inherits the parent's). Never name a vendor model. Hand the worker its inputs — it has no skill text of its own — and it does the work itself, no sub-spawning. Anything that asks the user stays in the main session. Fall back to inline only if your tool cannot spawn.
Setup
docs-builder.cjs sits next to this file in docs-builder/, installed or run from the package. Never search the target repo for it, never reconstruct it from this spec; if it exists nowhere, say so and stop. Set DB to its ABSOLUTE path, then cd to the target repo root:
DB=<absolute path to docs-builder.cjs>
cd <target repo root>
Every command below is node $DB …. Everything the script writes (docs/.docs-builder/* state, docs/index.md, docs/log.md, the ledger, the config pointer) lands under the target repo; REPO= is only needed when not running from its root.
Hard rules
- Only
.mdfiles are ever opened, read, edited or listed — a non-.mdfile is never touched, not even to report a mention. - Never moved, enforced in code:
README.md,index.md,log.md,CHANGELOG.md,LICENSE.md,CONTRIBUTING.md,CODE_OF_CONDUCT.md,SECURITY.md,CLAUDE.md,AGENTS.md,AGENT.md(case-insensitive, any depth), every dot-dir,node_modules/. - Nothing moves before the user approves the table. Only after approval does
apply-reorgrun; it refuses while any row'sbucketis empty. - Never split N files in one shot on a list the user has not seen.
reorgnever splits.cleanup <file.md>is the ONLY entry to the split pipeline: exactly one.mdfile, refuses a missing or protected one.cleanup-applyrefuses without alabels.jsonthat has exactly onecore: truetheme.- The original is always archived byte-identical (
git mvintodocs/archive/); every cleanup output is a new file, nothing edits a source doc. docs/index.mdhas exactly one writer:index-flat— never hand-edit it.- Never rewrite
CHANGELOG.mdorlog.mdlinks (any depth). Nothing underdocs/archive/is ever a rewrite target; links elsewhere that point at an archived file are still repaired. - Commit only through the printed pathspec recipe; never
git add -A,git add -uorgit commit -a.
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.
- 11d ago Changed · +2 lines 97cc849b1853
- 15d ago Changed · -809 lines 0756df0ba831
- 1mo ago Changed · +3 lines 602278ee862f
- 1mo ago Changed · +98 lines 45e518c584d3
- 1mo ago Changed · -3 lines · -3 tokens per session ea8338bcb00b
- 1mo ago First seen · 903 lines · 23 tokens per session scan A f37b490e6e9b
docs-builder is a command published in the GitHub repository hamr0/agentic-toolkit (22 stars, last pushed today), licensed Apache-2.0. It adds 20 tokens to every session and 4,320 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to docs-builder, differing in 0 lines, and is treated as a copy.
Other commands, from other repositories
agent-workflow
Automated multi-agent development workflow with quality gates from idea to production code.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.