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 refreshgit 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/refresh)<a href="https://agentmods.dev/skills/nick-railsback/skill-engine/refresh"><img src="https://agentmods.dev/badge/skills/nick-railsback/skill-engine/refresh/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/refresh"><img src="https://agentmods.dev/badge/skills/nick-railsback/skill-engine/refresh.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 | $0.00040 | $0.01903 |
| Opus 5.5 | $0.00016 | $0.00761 |
| Sonnet 5.5 | $0.00008 | $0.00381 |
| Haiku 4.5 | $0.00004 | $0.00190 |
Grade A, and why
refresh 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 — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Refresh
You receive a task: bring the contextualizer's existing references
into agreement with the current upstream state of every registered
source. The named checks in verify.sh (plus the permalink-density
lint for SHA-pinning) validate your output; the four reference
invariants are your authoring targets — not all are machine-checked
(see § Output contract). How you reason about drift is your call — there is no Stage -1/1/2/3 prescription, no
fixed keystroke menu, no required worker dispatch.
Contextualizer root
Engine workflows operate inside a contextualizer installed as a project skill at one of three install levels:
- User-level:
~/.claude/skills/<slug>-context/ - Local-user-level:
~/.claude/local/skills/<slug>-context/(when in use) - Project-level:
<repo>/**/.claude/skills/<slug>-context/
Every path below — research/..., references/..., verify.sh —
resolves relative to whichever directory matches. Before reading or
writing anything, locate the root by searching all three install
levels in order:
Run the script in shared/locator-block.md verbatim before proceeding.
CTX_PROPOSED="${CTX_ROOT}.proposed"
/skill-engine:refresh <name> names the contextualizer to refresh —
the directory name without the -context suffix; with no argument,
auto-detection applies. The staging-directory model (how
$CTX_PROPOSED mirrors the live tree and the sandbox-block diagnostic)
is in references/tool-and-output-mechanics.md.
Read it before your first write of a run.
Output contract
Two things, both load-bearing:
- Updated reference files in
references/(where applicable), each still citing its source by path plus content-hash (see02-artifact-contract.md). Each still satisfies the four reference invariants (definitions owned by02-artifact-contract.md§Navigator size budget and §Long references — do not restate them elsewhere):- first-5K — the navigator's standing instructions (invariants,
critical rules, dispatch logic) fit in the first 5K bytes of
SKILL.mdbody; the catalog table is a TOC and is exempt. - depth-1 — no more than one level of pointer indirection.
- max-100-line-TOC — any reference body over 100 lines carries a TOC marker within its first 30 lines.
- SHA-pin — every citation pins to a specific SHA, not a moving branch or tag.
- first-5K — the navigator's standing instructions (invariants,
critical rules, dispatch logic) fit in the first 5K bytes of
- Updates to
research/source-paths.jsonreflecting upstream transitions you detected (lifecycle.statefor each source;proposed_urlonmoved;last_checkedandlast_checked_shatimestamps). The four-state field onsource-paths.jsonis the single source of truth for upstream state.
What ships with it
2 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 a6751bd6bd88
- 1mo ago Changed · +1 lines 839a82016067
- 1mo ago First seen · 164 lines · 40 tokens per session scan A d5c3a569b61f
refresh is a skill published in the GitHub repository nick-railsback/skill-engine (2 stars, last pushed 6d ago), licensed MIT. It adds 40 tokens to every session and 1,903 once invoked, about $0.0002 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…