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 skills/tomthebearded/guide-forge/update-stacknpx skills add tomthebearded/guide-forge --skill update-stackgit clone --depth 1 https://github.com/tomthebearded/guide-forgeWhat 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 | $0.00173 | $0.00576 |
| Opus 5 | $0.00086 | $0.00288 |
| Sonnet 5 | $0.00035 | $0.00115 |
| Haiku 4.5 | $0.00017 | $0.00058 |
Grade A, and why
update-stack scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Skill: update-stack
The complete, canonical contract for this skill is the paste-prompt it wraps, inlined here — follow it in full:
!cat "${CLAUDE_SKILL_DIR}/prompt.md"
(If the block above came back empty or errored, read prompt.md in this skill folder — it sits beside this SKILL.md — and follow that.)
As you follow it, adapt for the fact that you're a Claude Code skill, not a pasted prompt:
- You're already invoked — skip its "How to use / paste this" preamble and its
{{TOOLS}}placeholder. The tools to bump are$ARGUMENTSbelow (a subset of tool names, or empty for all), plus any attached lockfile/manifest. Read the guide'sguide/files yourself where you can. - You have file tools here — edit the guide on disk under
guide/as the prompt directs, rather than only printing fenced blocks. - When the prompt hands off to
audit-guide(Phase 7), use the sibling skill/audit-guide.
Tools to bump / args:
$ARGUMENTS
Gate: run the prompt's Step 0 frontier gate first — read guide/foundation/progress.md, and if the
propagation would rewrite a step already executed, stop and present the three routes before writing any step
file (stack.md itself is always safe to bump). Touch only what the version bump actually affects; never mark
a rewritten milestone ✅ — the code changed, so the user must re-run the Done-when gates. Leave all changes in
the working tree — do not commit.
What ships with it
1 file 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.
- yesterday First seen · 43 lines · 173 tokens per session scan A cc890a7173b0
update-stack is a skill published in the GitHub repository tomthebearded/guide-forge (3 stars, last pushed 11d ago), licensed MIT. It adds 173 tokens to every session and 576 once invoked, about $0.0009 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 skills, from other repositories
writing
Draft, revise, audit, or transform human-facing prose: articles, blogs, documentation, criticism, essays, email, marketing and SEO copy, summaries, scripts, application materials, and UI text. Excludes code comments, commit messages, and private notes.
renhua
Chinese public-writing editor for AI/tech posts, X/Twitter threads, product notes, and public technical essays. Use for 去AI味, 改得像本人, 写推特post, 精修中文AI技术文章 — removes AI-flavored shells while preserving facts, judgment, technical terms, and author voice. Not for academic papers, codebase docs, bid documents, or…
document-writer
Write or update technical documentation grounded in the real codebase. Use when the user asks for README, API docs, architecture guides, user guides, CONTRIBUTING docs, migration notes, or JSDoc/code comments, or wants technical docs rewritten into natural Chinese with correct terminology. Not for general prose…
Documentation Gap Finder
Audits a codebase or docs folder and lists everything that is undocumented, outdated, or unclear.
Technical Blog Post Writer
Writes engaging, accurate technical blog posts targeted at developer audiences.
technical-writing
Use when drafting or revising internal technical design docs, review notes, architecture writeups, or sharing posts in Chinese, especially when the tone should stay evidence-backed, calm, and suitable for peers or leaders rather than marketing or literary writing.