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/draft-milestonenpx skills add tomthebearded/guide-forge --skill draft-milestonegit 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 | $0.00112 | $0.00565 |
| Opus 5 | $0.00056 | $0.00282 |
| Sonnet 5 | $0.00022 | $0.00113 |
| Haiku 4.5 | $0.00011 | $0.00056 |
Grade A, and why
draft-milestone scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Skill: draft-milestone
The complete, canonical contract for this skill is the paste-prompt it wraps, inlined here — follow it in full:
!cat "${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. What to draft is
$ARGUMENTSbelow (plus any attached reference files): empty → draft the whole guide (every milestone in the approved ladder); a milestone name (or list) → draft only those. - You have file tools here — where the prompt says to output the milestone files as fenced blocks, write them to disk in the milestone's folder (named per the canonical layout the prompt points to) instead, then summarize what you created.
- Where the prompt hands off to another prompt by filename, use the sibling skill of the same name
(
/clarify-step,/review-before-follow,/audit-guide).
What to draft (empty = the whole guide):
$ARGUMENTS
Cadence: by default draft the whole guide — every milestone in the approved ladder, in order,
back-to-back in one pass, without stopping between milestones. Each milestone is still a complete folder
that honors the full contract, and each milestone's cumulative handoff feeds the next. Do not pause for
the reader to "implement one" first — produce the finished guide, then the reader builds against it and
verifies each Done-when gate as they go. Only when $ARGUMENTS names a specific milestone (or list) do you
draft just those — for re-drafting or fixing one milestone in an existing guide.
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.
- 2d ago First seen · 43 lines · 112 tokens per session scan A 64c2f76f4e07
draft-milestone is a skill published in the GitHub repository tomthebearded/guide-forge (3 stars, last pushed 11d ago), licensed MIT. It adds 112 tokens to every session and 565 once invoked, about $0.0006 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
Technical Blog Post Writer
Writes engaging, accurate technical blog posts targeted at developer audiences.
adhd-friendly-ste-technical-writer
Use when writing, restructuring, or reviewing technical documentation for lower working-memory demand. Apply ASD-STE100-inspired sentence and vocabulary discipline, ADHD-friendly navigation, resumable steps, and observable results to tutorials, setup guides, runbooks, manuals, and engineering procedures.
diataxis
Classify, create, review, and maintain documentation using the Diátaxis framework — the four-quadrant system (tutorials, how-to guides, reference, explanation) that separates documentation by user need. Use this skill whenever the user wants to classify documentation into quadrants, perform a documentation gap…
technical-writing
Plan, draft, rewrite, or review developer-facing prose such as technical articles, tutorials, documentation, research reports, release analysis, case studies, RFCs, PR descriptions, and bug reports. Use when the requested deliverable is writing or editorial feedback, not implementation planning, code review, or…
shadow-tutor
Post-session programming tutor for a developer who wants to grow. Use after an AI-assisted coding session to learn from it — it picks the one load-bearing decision the AI made that you most likely don't truly understand, makes you predict why before it reveals (breaking the "I get it" illusion), teaches the why…
documentation
Technical writing, API docs, and documentation best practices.