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 skills add nick-railsback/skill-engine --skill engine-bootstrapgit clone --depth 1 https://github.com/nick-railsback/skill-engineWrote 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/skills/nick-railsback/skill-engine/engine-bootstrap)<a href="https://agentmods.dev/skills/nick-railsback/skill-engine/engine-bootstrap"><img src="https://agentmods.dev/badge/skills/nick-railsback/skill-engine/engine-bootstrap/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/nick-railsback/skill-engine/engine-bootstrap"><img src="https://agentmods.dev/badge/skills/nick-railsback/skill-engine/engine-bootstrap.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00029 | $0.01886 |
| Opus 5.5 | $0.00012 | $0.00754 |
| Sonnet 5.5 | $0.00006 | $0.00377 |
| Haiku 4.5 | $0.00003 | $0.00189 |
Grade A, and why
engine-bootstrap 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 1mo 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 — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Engine bootstrap
Scaffold a new contextualizer in the current directory. Take a list of source URLs or local paths from the user, auto-detect the metadata the engine needs, stamp the matching template set into place, and exit with a 3-line message naming the next workflow to run.
The user supplies sources. The engine fills in everything else.
Installation layout
A contextualizer is stamped as a self-contained Claude Code project skill at:
.claude/skills/<slug>-context/
├── SKILL.md
├── verify.sh
├── research/
│ ├── source-paths.json
│ └── .research-state.json
└── references/ (created by /skill-engine:discover later)
.claude/skills/<slug>-context/ is the contextualizer root. Every
engine workflow (discover, refresh, status, self-audit,
new-reference, using-skill-engine) resolves research/...,
references/..., and verify.sh relative to this root. The user invokes
slash commands from the project working directory (the parent of
.claude/); the workflows locate the root themselves.
Step 1 — Intake
Accept one or more sources: positional arguments (straight to Step 2)
or, with none supplied, an interactive loop reading pasted URLs/paths
until the literal word finish. --sources-file <path> plus
--branch-default-all batch-intake many sources at once. Recognition
table, disambiguator, edge case, and the batch-intake flags are in
references/intake-and-detection.md.
Step 2 — Auto-detection
For each accepted source, compute id, kind, and topology (single-
vs multi-source) without prompting — monorepo detection is deferred to
DISCOVER. Exact slug-derivation rules per input shape are in
references/intake-and-detection.md.
Step 2.4 — Confirm branch (git-managed sources only)
Ask once per git-managed source which branch to monitor; non-git
sources skip this entirely. Omitting the field on a default answer
(rather than recording an explicit main) keeps the entry correct if
the default branch is later renamed. Prompt copy and response handling
are in references/intake-and-detection.md.
What ships with it
3 files 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.
- 1mo ago Changed · -8 lines scan B → A 0568b17d6078
- 1mo ago First seen · 178 lines · 29 tokens per session scan B a8291a3cd274
engine-bootstrap is a skill published in the GitHub repository nick-railsback/skill-engine (2 stars, last pushed 6d ago), licensed MIT. It adds 29 tokens to every session and 1,886 once invoked, about $0.0001 per session on Opus 5.5. 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
product-discovery
File-first orchestrator for product discovery and spec frameworks. Frames the problem with a Discovery Lead, Product Analyst, or System Architect role. Spawns parallel framework agents (Double Diamond, How Might We, Jobs to Be Done, user stories with INVEST, EARS for AI-coder specs, Gherkin), synthesizes into a PRD or…
meta-prompt-optimizer
Audit and rewrite prompts against Claude Opus 4.7 instruction-following best practices. Produces a scored audit plus a rewritten prompt. Use when the user asks to audit, review, critique, rewrite, improve, optimize, tighten, score, fix, migrate, or draft a prompt — including system prompts, CLAUDE.md files, Claude…
product-strategy
File-first orchestrator for business and product strategy frameworks. Frames the challenge with a CPO / CSO / VP Design role, spawns parallel framework agents (Rumelt kernel + Crux, Wardley Maps, Minto Pyramid as thinking structure, Working Backwards PR-FAQ as discovery artifact), synthesizes outputs into one strategy…
research
Multi-agent research skill. Decomposes a question into 2–4 parallel Opus 4.7 research agents that write findings to per-agent Markdown files in real time, then runs a synthesis agent to merge by theme. Use when the user wants to research a topic, investigate something, find comparisons, compare options, learn about a…
ultraplan
Generator-critic planning. Launches 3 parallel Opus 4.7 explorers with distinct divergence vectors (architectural, speed-first, simple-first), each producing an independent plan, then runs a critic synthesis that composes the best elements into a single plan with per-decision attribution. Defeats single-agent…
product-design-shared
Shared canonical references for product-design frameworks — Pyramid Principle, Working Backwards, Double Diamond, research design, methodology selection. Consumed by product-discovery, product-strategy, working-backwards, and customer-research via ${ERPAVALHOME}/skills/product-design-shared/references/. Do NOT invoke…