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 duthaho/skillhub --skill tunegit clone --depth 1 https://github.com/duthaho/skillhubWrote 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/duthaho/skillhub/tune)<a href="https://agentmods.dev/skills/duthaho/skillhub/tune"><img src="https://agentmods.dev/badge/skills/duthaho/skillhub/tune/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/duthaho/skillhub/tune"><img src="https://agentmods.dev/badge/skills/duthaho/skillhub/tune.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 | $0.00157 | $0.02037 |
| Opus 5.5 | $0.00063 | $0.00815 |
| Sonnet 5.5 | $0.00031 | $0.00407 |
| Haiku 4.5 | $0.00016 | $0.00204 |
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 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 — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
tune — the harness retro
/tune — audit the current project's harness against recent sessions
/tune all — widen across every project under ~/.claude/projects/
Answer one question: what keeps going wrong across sessions, and what one-line change would make it impossible next time? Correcting the agent fixes one session; correcting the harness fixes every session after it. The evidence is already on disk — the transcripts recorded every correction, every retyped instruction, every permission prompt. This skill reads them so the user doesn't repeat them.
Step 0 — Scope, then inventory
Scope: default is the current project's transcripts — the last ~10
sessions or 2 weeks, whichever is smaller — from
~/.claude/projects/<project-dir>/*.jsonl (the dir name is the project
path with / → -). /tune all widens to every project; mining gets
shallower per project, say so.
Inventory the harness first — findings only mean something against the
baseline. Read: user + project CLAUDE.md, the installed skills (names +
descriptions), settings.json / settings.local.json (permissions,
hooks). Also read out/tune/learnings.md (past accepted/rejected — don't
re-propose what was rejected), out/tune/principles.md if present
(promoted cross-cutting principles — a lens for judging new findings),
and out/dev/bugfix-log.md if present (recurring root causes are harness
findings too).
Step 1 — Mine the transcripts (cheap models, parallel)
Bulk transcript reading is a job for a cheap model, not the frontier
one — spawn the miners with model: haiku, one per evidence stream,
concurrently:
- Corrections: user messages that correct, redo, or undo the agent's work — especially the same correction phrased across different sessions. The strongest signal there is.
- Friction: permission prompts approved again and again, commands the user retypes, tool errors hit repeatedly (a broken alias, a missing binary, a path that's always wrong the first time).
- Ignored rules: places where a
CLAUDE.mdrule already exists and the transcript shows it being violated anyway — prose that failed needs a mechanism, not more prose. - Re-derived procedures: multi-step sequences the agent works out from scratch in session after session — candidates for a script or a skill.
- Dead weight: rules and skills that never once became relevant in the mined window.
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 First seen · 168 lines · 157 tokens per session scan A 234f81fff9a8
tune is a skill published in the GitHub repository duthaho/skillhub (9 stars, last pushed 1mo ago), licensed MIT. It adds 157 tokens to every session and 2,037 once invoked, about $0.0006 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
analyze
Analyze a legacy app in any language before rewriting it in Elixir: inventory, features as goals, why each mechanism exists, runtime topology, external contracts. Use to start or refresh a rewrite.
session-deep-dive
Deep qualitative analysis of high-signal sessions. Spawns subagents with v2 template, synthesizes patterns, compares against known findings. Use after /session-scan.
tidewave-integration
Tidewave MCP runtime tools — debugging, smoke testing, live state inspection, SQL queries, hex docs. Use when evaluating code in a running Phoenix app.
plugin-dev-workflow
Guide plugin development workflow — editing skills, agents, hooks, or eval framework in this repo. Use when modifying files in plugins/elixir-phoenix/, lab/eval/, or lab/autoresearch/. Ensures changes pass eval, lint, and tests before committing.
elixir-idioms
OTP/BEAM patterns and Elixir idioms — GenServer, Supervisor, Task, Registry, pattern matching, with chains, pipes. Use when designing processes or debugging BEAM issues.
security
Build and harden Phoenix auth and security — OAuth login, password hashing, sessions, RBAC, rate limiting, CSRF, XSS, SQL injection, secrets. Use when adding login flows or permissions, or handling user input.