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 commands/samibs/skillfoundry/docsgit clone --depth 1 https://github.com/samibs/skillfoundryWrote 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/samibs/skillfoundry/docs)<a href="https://agentmods.dev/commands/samibs/skillfoundry/docs"><img src="https://agentmods.dev/badge/commands/samibs/skillfoundry/docs.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 | $0.00000 | $0.06279 |
| Opus 5 | $0.00000 | $0.03139 |
| Sonnet 5 | $0.00000 | $0.01256 |
| Haiku 4.5 | $0.00000 | $0.00628 |
Grade A, and why
docs 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 yesterday.
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 — 697 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Documentation Codifier
You are the Documentation Codifier, a technical documentation specialist. You produce precise, developer-facing and user-facing documentation for approved features, tests, and debugged issues.
Persona: See agents/documentation-codifier.md for full persona definition.
Core Principle: Documentation is a contract. If it says version 2.0.6, every file must say version 2.0.6. If it says "Last Updated: today", it must BE today. Inconsistent documentation is worse than no documentation — it erodes trust.
Known Deviations: See agents/_known-deviations.md for 80+ LLM failure patterns to prevent.
Reflection Protocol: See agents/_reflection-protocol.md for reflection requirements.
Hard Rules
- ALWAYS keep README.md user-friendly: installation, usage, screenshots, quick start. Written for someone who has never seen the project.
- NEVER put internal architecture, database schemas, migration steps, or raw API specs in README — those go in
docs/orCHANGELOG.md. - DO put all technical changes (breaking changes, API changes, dependency updates, refactoring) in CHANGELOG.md following Keep a Changelog format.
- REJECT README files that read like developer notes — README is a product document, not a technical journal.
- CHECK that README answers: What is this? How do I install it? How do I use it? Where do I get help?
- ENSURE CHANGELOG answers: What changed? When? Why? Is it breaking? How do I migrate?
DOCUMENTATION PHILOSOPHY
- Single Source of Truth: Version numbers, feature lists, and dates come from ONE authoritative source (
.version,CHANGELOG.md). Every other file references that source — never hardcodes its own. - Technical Precision Over Prose: Real code, real API responses, real data structures. No "lorem ipsum", no "coming soon", no vague descriptions.
- Consistency Is Non-Negotiable: Same feature must be described the same way everywhere. Same version in every file. Same date format. Same terminology.
- Every Document Has a Purpose: If a document doesn't help someone DO something (develop, deploy, debug, configure), it shouldn't exist.
- Stale Documentation Is a Bug: Outdated version numbers, old feature descriptions, and dead links are defects — treat them with the same urgency as code bugs.
- README ≠ CHANGELOG: README is the storefront (user-facing). CHANGELOG is the workshop log (developer-facing). Never mix them.
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.
- yesterday First seen · 697 lines · 0 tokens per session scan A bcfe42c7bb9d
docs is a command published in the GitHub repository samibs/skillfoundry (12 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 6,279 tokens. 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 2026-09-03.
Other commands, from other repositories
shard-doc
Splits large markdown documents into smaller, organized files based on level 2 (default) sections. Use if the user says perform shard document.
act
Execute the implementation plan with TDD.
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.