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 OutlineDriven/odin-gemini-cli-extension --skill tastegit clone --depth 1 https://github.com/OutlineDriven/odin-gemini-cli-extensionWrote 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-gemini-cli-extension/taste)<a href="https://agentmods.dev/skills/outlinedriven/odin-gemini-cli-extension/taste"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-gemini-cli-extension/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/outlinedriven/odin-gemini-cli-extension/taste"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-gemini-cli-extension/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 | $0.01420 |
| 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 7d 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.
This is a copy
100% identical to taste — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with 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.
- 7d ago First seen · 107 lines · 97 tokens per session scan B 37d6f7bd272b
taste is a skill published in the GitHub repository OutlineDriven/odin-gemini-cli-extension (5 stars, last pushed 2mo 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). It is 100% identical to taste, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
design
Set visual and interaction direction for any UI surface (web, React, TUI, CLI, desktop, Qt, design-system tokens) before any UI code. Direction-first: generates 3-4 distinct directions via verbalized sampling, picks one via per-axis single-select, then derives palette, typography, spacing, motion budget. Loads when…
askme
Verbalized Sampling (VS) protocol for intent exploration before planning, mode-aware. Default exhaustive runs full VS; collaborative runs tip-sharing dialogue; adversarial walks the design tree one fork at a time. Auto-detects from phrasing ("help me refine" → collaborative, "poke holes" → adversarial); override via…
grill-ai-mastery
Hybrid interview that probes AI-engineering mastery by tip-vocabulary depth — entity referencing, loop closure, observability, harness improvement — not by token usage or LOC. Start collaborative (two-way tip exchange), escalate to adversarial probing when depth is lacking. Trigger when the user says "interview me on…
grill-me
Adversarial relentless interview against any plan or design until shared understanding is reached. Walk the decision tree, resolve dependencies one answer at a time, recommend a default per question. Trigger when the user says "grill me", "stress-test this", "interview me about this design", or otherwise asks for…
git-branchless
Enforce idiomatic git-branchless during planning and executing tasks — detached-HEAD-first work, in-memory rebase via git move, event-log recovery via git undo, deferred branch creation, speculative-merge git sync for base updates. Use when planning or executing multi-commit work, history rewrites, stack edits…
proof-driven
Proof-driven development. Use when implementing with formal verification using property-based testing, theorem proving, or proof tactics; zero unproven property policy enforced.