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/scolladon/craft/tunenpx skills add scolladon/craft --skill tunegit clone --depth 1 https://github.com/scolladon/craftWrote 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/scolladon/craft/tune)<a href="https://agentmods.dev/skills/scolladon/craft/tune"><img src="https://agentmods.dev/badge/skills/scolladon/craft/tune.svg" alt="Measured on agentmods" 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 | $0.00065 | $0.01894 |
| Opus 5 | $0.00032 | $0.00947 |
| Sonnet 5 | $0.00013 | $0.00379 |
| Haiku 4.5 | $0.00006 | $0.00189 |
Grade A, and why
tune 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 5d 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 — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
craft:tune — feedback-driven config tuner (propose-diff)
Standalone session-owned skill. You (the session) read the usage signals the miner
already produced, ask the plan computer for a proposed patch to a NAMED config, present
the diff, and land it through the existing lint-then-move bin only after you confirm with
the user. No worker agent is spawned. This is the ACTING half of the observe→improve loop:
craft:metrics mines (read-only); craft:tune acts. It NEVER touches .claude/workflow.md
and NEVER auto-applies — the human confirm is the gate.
Input: $ARGUMENTS — <name> (required), plus optional --report <path>.
Preamble — probe + resolve (read-only)
1. Plugin root
Confirm both entrypoints this skill composes exist:
test -f "${CRAFT_ROOT:-${CLAUDE_PLUGIN_ROOT}}/engine/bin/tune-plan.js"
test -f "${CRAFT_ROOT:-${CLAUDE_PLUGIN_ROOT}}/engine/bin/init-land.js"
If either test fails, surface a diagnostic and stop — the plugin installation is incomplete.
Parse $ARGUMENTS:
<name>— required. Absent ⇒ STOP: "a config name is required".--report <path>— optional. Defaultreport.jsonat the repo root.
2. Report presence (the acting precondition)
The tuner acts on the miner's output; it does not mine transcripts itself.
report="${report_arg:-report.json}"
test -f "$report"
If the report is absent, STOP: "no report.json found — run /craft:metrics first to mine
the usage signals this tuner acts on." This is the CQS boundary: observe (metrics) before act
(tune).
3. Base config resolution (two-scope)
Locate the named config to patch across local then user scope — the same resolver
/craft:run --config uses:
base="$(node "${CRAFT_ROOT:-${CLAUDE_PLUGIN_ROOT}}/engine/bin/config-resolve.js" "$name")"
Non-zero exit ⇒ STOP — surface the stderr diagnostic verbatim (the resolver names both scopes
it looked in). The tuner patches an EXISTING named config; it never seeds a fresh one and never
falls back to .claude/workflow.md.
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.
- 5d ago First seen · 177 lines · 65 tokens per session scan A 8fa1a74370fb
tune is a skill published in the GitHub repository scolladon/craft (2 stars, last pushed 17d ago), licensed MIT. It adds 65 tokens to every session and 1,894 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 skills, from other repositories
great_cto
Use when the CTO describes a feature, task, or project goal. Orchestrates the full SDLC pipeline automatically based on project type.
define
Manifest builder. Turns shared understanding into a verifiable Manifest with Deliverables, Acceptance Criteria, Global Invariants, and an Initial Approach. Use when planning features, scoping refactors, debugging complex issues, or when the user asks to define, scope, plan, spec out, make a manifest, or break down a…
vertical-real-estate
Residential-proptech domain knowledge so architect / pm aren't naive when speccing real-estate products (listings, lead-crm, transaction-coordination, property-mgmt). Codifies MLS/IDX reality, listing status lifecycle + syndication canonical-source, long-cycle lead nurture, transaction-coordination as the high-pain…
skeptical-triage
Reusable 3-round self-challenge + arbiter pattern for filtering false positives from findings/verdicts. Use when the cost of a false-positive gate block exceeds the cost of 4 extra LLM turns.
anti-patterns
Catalogue of known SDLC anti-patterns that greatcto agents must actively reject when reviewing architecture, plans, code, or post-mortems. Used by architect (pre-impl), pm (planning), senior-dev (impl), l3-support (post-incident).
cost-model
Standardized cost-estimation framework for greatcto plans. Forces explicit LLM cost, infra cost, human-supervision time, and the (defensible) human-equivalent comparison. Output format is parsable by the board's /api/cost path — must follow exactly.