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/nick-railsback/skill-engine/releasegit clone --depth 1 https://github.com/nick-railsback/skill-engineWhat 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 | $0.00053 | $0.03875 |
| Opus 5 | $0.00026 | $0.01937 |
| Sonnet 5 | $0.00011 | $0.00775 |
| Haiku 4.5 | $0.00005 | $0.00387 |
Grade A, and why
release 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.
How it starts
The opening of the file, as written. The whole thing — 255 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Release skill-engine
You are shepherding the maintainer through a release of the skill-engine repository. Follow the phases in order. Halt on any error.
Standing constraint: You MUST NOT run git add, git commit, git push, git tag, or gh release create on the maintainer's behalf, even if the workflow seems to call for it. Phases 1-5 below prepare every artifact; Phase 6 then surfaces the exact commands the maintainer should run themselves. This rule overrides any sub-skill or template that prescribes auto-commit. The two destructive gates (commit/push and tag/release) are the maintainer's call, every time.
Argument parsing
The maintainer invoked with $ARGUMENTS. Resolve as follows:
- Empty → ask interactively: "Which bump?
major,minor,patch, or an explicitX.Y.Z?" major/minor/patch→ read the current version (Phase 2), then compute the next per the rules:major:X+1.0.0(e.g.,0.2.0→1.0.0)minor:X.Y+1.0(e.g.,0.2.0→0.3.0)patch:X.Y.Z+1(e.g.,0.2.0→0.2.1)
X.Y.Zmatching^[0-9]+\.[0-9]+\.[0-9]+$→ use the literal value. Still show "current → new" and confirm.- Anything else → reject and fall back to interactive.
Store the resolved value as NEW_VERSION. Use it in every subsequent phase.
When to pick which bump (from plugin/skill-engine/docs/06-release-doctrine.md):
| Bump | When |
|---|---|
major |
Breaking change to the install layout, the metadata schema, or the navigator structure. Triggers a legacy-upgrade flow on existing installs. |
minor |
New CLI feature, new reference file added to the catalog, new engine workflow, new source kind. |
patch |
Reference content updates, bug fixes, doc fixes that change what users see after running update. |
Internal-only changes (engine refactors, tooling, doc-only updates to this repo's own materials) go into an [Unreleased] CHANGELOG section and roll into the next real release — they do NOT get their own patch bump. If $ARGUMENTS is patch but all the changes since the last tag are internal-only, surface that observation and ask the maintainer to reconsider.
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 · 255 lines · 53 tokens per session scan A 02b77c45478b
release is a command published in the GitHub repository nick-railsback/skill-engine (2 stars, last pushed 25d ago), licensed MIT. It adds 53 tokens to every session and 3,875 once invoked, about $0.0003 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 commands, from other repositories
spec-forge
Use when generating software specifications — full chain (Idea→Decompose→Tech Design + Feature Specs) or individual documents.
propagate
Use after editing an upstream doc (PRD/SRS/tech-design/feature-spec) to propagate changes downstream and keep the entire doc chain consistent.
analyze
Use when analyzing a document collection to map themes, find conflicts, gaps, and redundancies — generates landscape analysis report.
review
Use when reviewing spec-forge generated documents for quality, completeness, and consistency — auto-fixes issues if found.
audit
Use when auditing existing project docs for quality, completeness, and code alignment — generates findings report with fix recommendations.
tech-design
Use when writing a tech design, architecture doc, RFC, or design document — follows Google Design Doc format.