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 sssstwee/tastedistill --skill distillgit clone --depth 1 https://github.com/sssstwee/tastedistillWrote 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/sssstwee/tastedistill/distill)<a href="https://agentmods.dev/skills/sssstwee/tastedistill/distill"><img src="https://agentmods.dev/badge/skills/sssstwee/tastedistill/distill/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/sssstwee/tastedistill/distill"><img src="https://agentmods.dev/badge/skills/sssstwee/tastedistill/distill.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 | $0.00074 | $0.02657 |
| Opus 5.5 | $0.00030 | $0.01063 |
| Sonnet 5.5 | $0.00015 | $0.00531 |
| Haiku 4.5 | $0.00007 | $0.00266 |
Grade B, and why
distill scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- `$HOME/.codex/config.toml` without copying secrets or volatile machine state Copies of this mod
1 near-identical copy found in the catalogue:
- tasted-distill — 97% identical, 12 lines differ
How it starts
The opening of the file, as written. The whole thing — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Distill: Improve The Next Run
Use this skill after meaningful work has produced a lesson.
Prefix your first response line with ⚗️ inline, not as its own paragraph.
Before the workflow, apply ../../shared-rules/host-compatibility.md, ../../shared-rules/portable-profile.md, and ../../shared-rules/personalization.md for explicit TasteD/TasteDistill invocations. If this skill is already running the Local Personalization Bootstrap, use those shared rules only as host-safety, idempotence, and destination policy.
Apply ../../shared-rules/runtime-hygiene.md when distillation reads logs, creates generated evidence, invokes helper scripts, or runs browser/runtime checks.
Apply ../../shared-rules/memory-protocol.md when the request involves cross-agent memory, host memory refresh, profile sync, or memory health checks.
Outcome Contract
- Outcome: current work improves future agent behavior through reusable guidance with scope, trigger, evidence, and destination.
- Done when: each lesson is classified as update now, keep candidate, or discard, and the chosen destination is the narrowest useful one.
- Evidence: user corrections, failed attempts, verified fixes, tests, command output, diffs, logs, delivery results, and stable project conventions.
Taste Distillation Loop
work -> evidence -> lesson -> durable rule -> better next run
Distillation is not a transcript summary. It turns repeated, verified behavior into future execution guidance. A lesson should explain when the agent should behave differently next time, what evidence supports the rule, and where the rule belongs.
Local Personalization Bootstrap
Use this mode when the user asks to initialize these skills from their existing Codex or compatible agent memory, conversation history, logs, or prior task outcomes.
Do not assume those sources are already loaded. Installing a skill does not automatically import a user's historical conversations or memories. Explicitly invoking the TasteD/TasteDistill plugin or any tasted-* skill should perform a one-time bootstrap check through ../../shared-rules/personalization.md. If no local TasteDistill profile exists, run this bootstrap before continuing with the requested skill.
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.
- 2mo ago First seen · 175 lines · 74 tokens per session scan B b1adc13627c4
distill is a skill published in the GitHub repository sssstwee/tastedistill (2 stars, last pushed 5mo ago), licensed MIT. It adds 74 tokens to every session and 2,657 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
weekly-digests
Generate a serial week-by-week narrative digest of a project's full claude-mem timeline. Splits the timeline into per-ISO-week files, then runs one consecutive subagent per week — each receiving the prior week's carry-forward block — to produce one chapter per ISO week of data. Use when asked for "weekly digests"…
cloud-sync
Set up or check claude-mem cloud sync with cmem.ai Pro. Use when the user says "set up cloud sync", "sync my memories", "cmem pro", "cloud backup", "sync status", or wants their memory database backed up or synced to their cmem.ai account.
screenpipe
Search screen and audio history recorded by Screenpipe and optionally save selected context into claude-mem. Use when the user asks to recall desktop activity, a meeting, or something seen in another app through Screenpipe.
memory-retain
Save what was learned to Hindsight long-term memory. Use when a task finishes, when the user states a fact, decision or preference, and when you discover something a later run or another Bot would need.
hivemind-memory
Global team and org memory powered by Activeloop. ALWAYS check BOTH built-in memory AND Hivemind memory when recalling information.
honcho-integration
Integrate Honcho memory into existing Python or TypeScript codebases. Use when adding Honcho SDK, setting up peers, configuring sessions, and accessing Honcho's representation.