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/nick-railsback/skill-engine/engine-bootstrapnpx skills add nick-railsback/skill-engine --skill engine-bootstrapgit 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 | $0.00029 | $0.01909 |
| Opus 5 | $0.00015 | $0.00955 |
| Sonnet 5 | $0.00006 | $0.00382 |
| Haiku 4.5 | $0.00003 | $0.00191 |
Grade B, and why
engine-bootstrap scanned grade B with 1 finding 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.
Enumerates other installed skillsmediumAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
find .claude/skills -mindepth 1 -maxdepth 1 -type d -name '*-context' 2>/dev/null How it starts
The opening of the file, as written. The whole thing — 178 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.
Activation guard
This skill assumes no contextualizer is installed under
.claude/skills/*-context/ yet.
-
From the project working directory, look for an existing contextualizer:
find .claude/skills -mindepth 1 -maxdepth 1 -type d -name '*-context' 2>/dev/nullIf any match is a non-empty directory, surface a one-line warning naming the path, list the files that would be overwritten, and pause for explicit confirmation before continuing. The condition is files-present, NOT a parseable
research/.research-state.json: a corrupted state marker must not bypass this guard, because the directory may still hold a curatedSKILL.mdand a populatedresearch/source-paths.jsonthat stamping would overwrite. Theusing-skill-enginerouter sends both new and corrupt-marker directories here; either way, existing files pause for confirmation. -
Otherwise, proceed.
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. Intake asks exactly one content
question and zero engine-taxonomy questions — never kind,
source_id, scope, or topology directly. Recognition table,
disambiguator, and edge case 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.
- 2d 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 25d ago), licensed MIT. It adds 29 tokens to every session and 1,909 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
skill-creator
Create or improve Zhin Agent skills (SKILL.md). Use when asked to add a skill, write SKILL.md, document a repeatable agent workflow, or refine skill frontmatter/keywords. Triggers: 创建技能, 写 SKILL, skill-creator, 加 skill.
skill-sync-checker
Detects content drift between skill files and their source documents. Helps maintain skills that are derived from other documentation by comparing content and flagging outdated sections.
erpaval
Workflow for autonomous software development with the Kiro CLI (open Agent Skills standard). Classifiers route scope, complexity, directory state, and spec readiness before committing to Explore / Research / Plan / Act / Validate, then close the loop with a Compound step that persists lessons to .erpaval/solutions/…
skill-creator
Guide for creating effective agent skills. Use when you want to create a new skill, improve an existing skill, or learn best practices for skill development. Helps codify learned patterns into reusable, discoverable skills.
agent-ux-patterns
Agent UX patterns and human-in-the-loop design: Twilio A2H protocol, Levels of Autonomy (L0-L5), inbox pattern, progressive trust, decision journal, gate reviews, autonomous work reports. Six-phase methodology from vague pain point to concrete data model via landscape research and multi-direction brainstorming. Use…
Agent Instruction Drift Check
Procedure for comparing an agent-facing instruction doc (AGENTS.md/CLAUDE.md-style) against the actual current code and configuration to find and flag mismatches.