Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
Wrote 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/generate-my-taste)<a href="https://agentmods.dev/skills/outlinedriven/odin-gemini-cli-extension/generate-my-taste"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-gemini-cli-extension/generate-my-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/generate-my-taste"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-gemini-cli-extension/generate-my-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 | $0.00082 | $0.02273 |
| Opus 5 | $0.00041 | $0.01137 |
| Sonnet 5 | $0.00016 | $0.00455 |
| Haiku 4.5 | $0.00008 | $0.00227 |
Grade A, and why
generate-my-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 11d 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.
This is a copy
100% identical to generate-my-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 — 219 lines — stays where its author put it; the contents beside it link to each section on GitHub.
generate-my-taste
Generate a personal Claude Code taste skill from local evidence. The output is a <name>-taste skill shaped like spine / taste: frontmatter, posture, modes, two-sided charter, anchors, audit output shape, anchor mode output shape, auto-clarity exception.
Evidence leads. Questions confirm. Generation writes only after a preview gate.
Posture
Derive taste from observed patterns, not self-report alone. Mine memories and local agent histories for repeated positive influences, Side A slop bans, and Side B overkill bans. Convert those signals into exactly 5 portable anchors unless the user explicitly selects update-in-place for an existing owned skill with a different anchor count.
Keep the generator right-sized: one generated SKILL.md, references/anchors.md, and references/charter.md. No scripts, no evals, no SOUL file, no elegance file, no examples skeleton.
Modes [LOAD-BEARING]
Mode-selection
This skill has one mode: generate. If invoked for audit of an artifact, route to an existing taste/spine skill instead.
generate mode procedure
- Resolve the target name.
- Scan evidence sources.
- Extract influence, slop, and overkill signals.
- Ask compact confirmation forks.
- Compose and show the synthesis preview.
- Write generated references first and generated
SKILL.mdlast. - Report written paths and verification notes.
Evidence scan order
Prefer indexed sources when available; fall back to files. Missing sources are not failures.
- Indexed ICM tools or memory search tools exposed by the current harness.
- Indexed session-history tools exposed by the current harness.
- Local memory files:
/home/alpha/.claude/projects/**/memory/*.md/home/alpha/.claude/projects/**/memory/**/*.md/home/alpha/.claude/CLAUDE.md/home/alpha/.claude/CLAUDE.local.md
- Local transcript and conversation stores, when readable:
- Claude Code project histories under
/home/alpha/.claude/projects/ - Codex histories under common local config paths
- Gemini CLI histories under common local config paths
- OpenCode histories under common local config paths
- Amp histories under common local config paths
- Pi histories under common local config paths
- Cursor histories under common local config paths
- Claude Code project histories under
What ships with it
6 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.
- 11d ago First seen · 219 lines · 82 tokens per session scan A 5ce044e84961
generate-my-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 82 tokens to every session and 2,273 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to generate-my-taste, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
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…
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…
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…
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…
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.