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/outlinedriven/odin-codex-plugin/tastenpx skills add OutlineDriven/odin-codex-plugin --skill tastegit clone --depth 1 https://github.com/OutlineDriven/odin-codex-pluginWrote 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/outlinedriven/odin-codex-plugin/taste)<a href="https://agentmods.dev/skills/outlinedriven/odin-codex-plugin/taste"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-codex-plugin/taste.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 | $0.00097 | $0.01420 |
| Opus 5 | $0.00048 | $0.00710 |
| Sonnet 5 | $0.00019 | $0.00284 |
| Haiku 4.5 | $0.00010 | $0.00142 |
Grade B, and why
taste scanned grade B with 1 finding 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 4d 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.
Recursive force deletemediumDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- Destructive or irreversible operation confirmations (e.g., `git push --force`, `rm -rf`). Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Taste
Distinctive judgment over centroid-AI default convergence. Restraint as default. One strong intentional moment per artifact. The two failure modes — slop and overkill — are reciprocal: both come from refusing to commit. Slop hedges by averaging into AI defaults; overkill hedges by piling on decoration that covers thin ideas.
/taste operates across prose, code, design, and decisions with the same charter and the same eight anchors. It is a judgment register; it does not transform the artifact, it decides what about the artifact is committed and what is hedge.
Modes [LOAD-BEARING]
Mode-selection (hybrid)
Auto-detect from the user's phrasing, with slash-arg override:
- User wording matches
is this slop?,overkill?,elegant?,audit,taste-test this,judge this→ audit mode. - User wording matches
taste anchor,taste mode,taste register, or anticipates producing fresh work → anchor mode. - Anything else → audit (default; cheaper to run; no behavior commitment).
- Explicit override:
/taste audit,/taste anchor. Override always wins.
audit mode procedure
Walk the eight anchors one at a time against the artifact. For each: state the anchor, judge the artifact (pass / warn / fail), cite the Side A or Side B charter row when violated, and write a concrete fix. Close with the top-3 ranked fixes. Conflict-handling: when two anchors fail with conflicting fixes (e.g., Restraint says compress, Generosity says expand), surface the tension explicitly — no auto-pick, no fixed precedence list. Tie-break is user-led.
anchor mode procedure
Load the charter and anchors as imperatives the model will honor across subsequent responses. Persistence is best-effort: applies until the user signals "stop taste" or "normal mode" OR context is compacted, whichever comes first. Re-invoke /taste anchor if drift is observed. The model honors a directive loaded once into context.
The two-sided charter
Side A — slop (centroid-AI default convergence): generic openers ("Sure!", "Of course"), hedge-stacks ("perhaps it might be"), validation phrases ("you're absolutely right"), AI-flat prose with no rhythm, default palettes, defensive nil-checks where impossible, 50/50 decision hedges that pick nothing.
What ships with it
3 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.
- 4d ago First seen · 107 lines · 97 tokens per session scan B 37d6f7bd272b
taste is a skill published in the GitHub repository OutlineDriven/odin-codex-plugin (15 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 97 tokens to every session and 1,420 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it B with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
triage-issue
Investigate a reported bug to root cause, then emit a TDD-shaped fix plan as an issue artifact. Trigger when the user reports a bug, says "triage", asks for issue investigation, or wants a fix plan before code changes.
git-guardrails-claude-code
Install a Claude-Code PreToolUse hook that blocks destructive git commands (push variants including force-push, hard reset, force clean, branch -D, checkout/restore overwrites) before Bash runs them. Use when the user wants git safety rails, force-push prevention, or repository-wipe protection.
duet
Two-party posture — user as director, agent as executor; every fork, tradeoff, or choice surfaced via batched AskUserQuestion with a recommended default. Use when the user invokes /duet, says "ask before" / "pair with me" / "human-in-the-loop", or for aesthetic/architectural/irreversible decisions.
explore
Read-only codebase exploration: discovery, structural reading, and emission of architecture/pattern/tooling/dependency summaries. Use to understand existing code, map files, trace function flow, locate symbols, or build pre-implementation context. Uses a staged 1/3/5 Explore-agent escalation protocol scaled to scope.…
deps-upgrade
Dependency-upgrade campaign — outdated scan, batch-by-severity, breaking-change remediation, lockfile audit. Use when CVEs require remediation, when a major upstream version lands, when stack compatibility forces a sweep, or on a scheduled (quarterly) hygiene cadence. CVE-driven bumps consume security audit findings…
design-by-contract
Design-by-Contract (DbC) development. Use when implementing with formal preconditions, postconditions, and invariants across any language.