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 martinemde/dotfiles --skill tastegit clone --depth 1 https://github.com/martinemde/dotfilesWrote 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/martinemde/dotfiles/taste)<a href="https://agentmods.dev/skills/martinemde/dotfiles/taste"><img src="https://agentmods.dev/badge/skills/martinemde/dotfiles/taste/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/martinemde/dotfiles/taste"><img src="https://agentmods.dev/badge/skills/martinemde/dotfiles/taste.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 | $0.00097 | $0.02363 |
| Opus 5.5 | $0.00039 | $0.00945 |
| Sonnet 5.5 | $0.00019 | $0.00473 |
| Haiku 4.5 | $0.00010 | $0.00236 |
Grade A, and why
taste 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 24d 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 — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Taste
Reverse-engineered from 636 recorded sessions (~/lode/taste). CLAUDE.md already carries
the rules that hold regardless of task. This carries the ones that need a task to be true.
Debugging
Nearly half of all sessions open with "this thing I own is misbehaving," so assume this until told otherwise.
He wants the cause, not relief. He will live with a broken system if it means fixing it upstream properly. A diagnosis that does not mechanically produce the symptom he observed is not accepted — "I don't see how that would cause this effect?"
- Extracting the signal from the pasted evidence is your job.
- He states his hypothesis hedged and wants it overturned. Contradicting his guess with evidence is the point. Restating his guess back to him is worthless.
- Sanity-check the layer below before blaming the layer above.
- Never offer a menu of remediations while the cause is still unknown. He rejects the whole menu and redirects to diagnosis.
- Losing evidence scares him. Don't patch to fix if it hides the cause.
How much to build
| Situation | Which way |
|---|---|
| Upstream, someone else's repo | Surgical. Minimal diff. "Nothing more or less." |
| His own repo | Refactor freely; structural rewrites are welcome. |
| The shipped surface, or anything a user configures | Ruthlessly simple. A settled fact ships as a constant, not a knob. |
| Measurement, analysis, investigation, content | As elaborate as it takes. He'll ask for a twelve-phase calibration harness the same week he demands the result ship as one hardcoded number. |
| Considering an abstraction | Only if the piece becomes independently testable. "That way we can test it on its own" is the justification he accepts. Generality alone is not. |
| Designing a command | Narrow what it does, widen what it accepts. --write should only write, and should take a file path, not just a dir. |
| Flags on a tool | Human-invoked: keep -h/--help for discoverability. |
| A dependency is broken | If he still wants the thing: fork and fix it, however many lines. If it's optional and blocking a bootstrap: delete it. Ask which before proposing a repair. |
| Starting to build | If he can see the result and undo it in seconds (dashboards, YAML): iterate, no planning. A library, integration, or protocol client: PoC it first, then spec. |
| Picking a model or paying for compute | Cheapest thing that clears the bar for infrastructure he operates. Quality is non-negotiable in the thing he's building. |
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.
- 24d ago Changed · +6 lines be053909bc33
- 1mo ago Changed a286d9762174
- 1mo ago First seen · 168 lines · 97 tokens per session scan A a1e6d5f69dff
taste is a skill published in the GitHub repository martinemde/dotfiles (10 stars, last pushed yesterday), licensed ISC. It adds 97 tokens to every session and 2,363 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 2026-09-03.
Other skills, from other repositories
full-review
Full review: read every repo area, apply verified fixes, and prove all checks pass.
ast-grep
Search, outline, and rewrite code structurally with ast-grep rules.
chrome-devtools
Debug Chrome with DevTools MCP: console, network, performance, accessibility.
diagnose-ci
Investigate failing REMOTE CI runs on GitHub Actions: find the failed run, pull the failed-step logs with gh, identify the root cause (compile error, test failure, lint, missing secret, timeout), and recommend a fix. Read-only: it does not commit, push, or edit. Use when CI is red, a GitHub Actions run failed, or the…
systematic-debugging
Debug failures to root cause: DNS/TLS, Python CPU/memory with Pyinstrument and Memray.
incident-response
Handle live incidents: triage, containment, recovery, and communication.