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/mark-progressnpx skills add tomthebearded/guide-forge --skill mark-progressgit 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 | $0.00139 | $0.00684 |
| Opus 5 | $0.00069 | $0.00342 |
| Sonnet 5 | $0.00028 | $0.00137 |
| Haiku 4.5 | $0.00014 | $0.00068 |
Grade A, and why
mark-progress scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Skill: mark-progress
The complete, canonical contract for this skill is the paste-prompt it wraps, inlined here — follow it in full:
!cat "${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 the reader executed is
$ARGUMENTSbelow (plus any attached files). Read the guide'sguide/files yourself: the ledger, the status doc, and the milestone folders you need to name a step correctly. - You have file tools here — write
guide/foundation/progress.mdandguide/foundation/status.mdon disk, rather than only printing fenced blocks. Create the ledger fromtemplates/progress.md(deriving its rows from the step files actually on disk) if it's missing. - Marks only — touch nothing else. Do not edit step files, overviews,
glossary.md,stack.md,conventions.md,decision-log.md, or the guideREADME.md. Two files, and no others. - A big claim is worth checking before you record it. For a run of steps, a whole milestone, or work done
a while ago, offer the sibling skill
/check-my-workfirst — it reads the reader's real project back against the milestone checkpoints and tells you what actually landed. Offer, don't insist; then mark what comes back. - When the reader wants the guide changed, hand off to the sibling skill
/amend-guide; for friction,/log-feedbackor/report-issue. Say so; don't do their job here.
What was executed / args:
$ARGUMENTS
Gate: mark exactly what the reader claimed and nothing more — no ticking earlier steps on the assumption
they must be done, no ✅ on a milestone whose NN_verify.md gate wasn't confirmed, no silent resolution of a
ledger that already disagrees with status.md. Leave the 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.
- 2d ago First seen · 47 lines · 139 tokens per session scan A 42c617e3cee2
mark-progress is a skill published in the GitHub repository tomthebearded/guide-forge (3 stars, last pushed 11d ago), licensed MIT. It adds 139 tokens to every session and 684 once invoked, about $0.0007 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
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…
diataxis-docs-framework
Enterprise technical documentation best practices, patterns, and frameworks for developer and partner adoption. Covers content architecture (Diataxis four quadrants), 14 content types (tutorials, how-to guides, API reference, SDK docs, migration guides, changelogs, runbooks, integration guides, troubleshooting…
codetrain
Use when the user wants to be taught/walked through code one tiny step at a time — triggers like "teach me this code", "walk me through this", "hold my hand", "explain step by step", "tutor me", "guide me through", "I want to learn this", or asks for a safe practice exercise to learn a concept.
learning-tutor
Use when a developer wants to learn about the codebase, start a learning session, understand how something works, or progress through the curriculum. Activates when the intent is learning rather than doing. Trigger phrases: "I'm new here", "walk me through", "help me understand", "start a learning session", "what…
curriculum-reviewer
Use when reviewing AI-generated curriculum content in the human review queue. Activates when working through .codebase-mooc/memory/humanreviewqueue.jsonl or when asked to review, approve, or assess generated curriculum content. Trigger phrases: "review the curriculum", "check the review queue", "approve this content"…
trulens-notebook-execution
Execute and display Jupyter notebooks for TruLens demos and quickstarts.