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 using-skill-enginegit 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/using-skill-engine)<a href="https://agentmods.dev/skills/nick-railsback/skill-engine/using-skill-engine"><img src="https://agentmods.dev/badge/skills/nick-railsback/skill-engine/using-skill-engine/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/using-skill-engine"><img src="https://agentmods.dev/badge/skills/nick-railsback/skill-engine/using-skill-engine.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 | $0.00101 | $0.02104 |
| Opus 5.5 | $0.00040 | $0.00842 |
| Sonnet 5.5 | $0.00020 | $0.00421 |
| Haiku 4.5 | $0.00010 | $0.00210 |
Grade A, and why
using-skill-engine 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 — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Using the skill engine
This is the entry-point skill. It detects whether the current directory holds a contextualizer that has already been set up, and routes to the matching workflow.
Routing
When invoked, do the following in order. A contextualizer is installed at
one of three install levels: ~/.claude/skills/, ~/.claude/local/skills/,
or <repo>/.claude/skills/ at the project level. The project level is not
only the directory sitting at the repository root — it reaches any nested
.claude/skills/ below it, so a contextualizer can live beside the slice of
the code it describes. A contextualizer's research/.research-state.json is
the canonical setup-state marker.
Resolve what is installed with the script in
shared/locator-block.md, the engine's one
root-resolution definition — this skill does not carry a root list of its
own. The script exits on both the nothing-found and the several-found-and-
none-named paths, so it leaves no count behind in a variable; run it with
its enumeration flag and read its stdout instead:
ctx_all=$(bash -s -- --all <<'LOCATOR'
# …the fenced script from shared/locator-block.md, verbatim, with its
# name="<name>" line substituted to name="" …
LOCATOR
) && ctx_count=$(printf '%s\n' "$ctx_all" | grep -c '^/' || true) || ctx_count=0
[ "$ctx_count" -gt 0 ] || ctx_all=""
ctx_root=$(printf '%s\n' "$ctx_all" | head -n1)
Exit 0 means the enumeration printed one absolute path per line, and
ctx_count is that line count. Any non-zero exit means none was found, so
ctx_count is 0 and what landed on stdout is the script's own diagnostic
sentence rather than a path — which is why ctx_all is cleared on that
branch before anything reads it.
Pending-proposal pre-step (runs before case dispatch)
Before dispatching to a workflow, check for pending proposals — any
*-context.proposed/ directory that DISCOVER or REFRESH left behind. A
proposal is always staged as a sibling of the live contextualizer it was
derived from, so the enumeration above is most of the input this needs: the
install roots it names, deduplicated, are what gets searched. Each root
is searched once, and the three fixed roots are searched whether or not the
enumeration reached them:
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 · +32 lines 60b789829617
- 1mo ago First seen · 135 lines · 101 tokens per session scan A dde346e1374c
using-skill-engine is a skill published in the GitHub repository nick-railsback/skill-engine (2 stars, last pushed 6d ago), licensed MIT. It adds 101 tokens to every session and 2,104 once invoked, about $0.0004 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…