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 aaronartistzhang-afk/DailyWork --skill skill-evolve-loopgit clone --depth 1 https://github.com/aaronartistzhang-afk/DailyWorkWrote 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/aaronartistzhang-afk/dailywork/skill-evolve-loop)<a href="https://agentmods.dev/skills/aaronartistzhang-afk/dailywork/skill-evolve-loop"><img src="https://agentmods.dev/badge/skills/aaronartistzhang-afk/dailywork/skill-evolve-loop/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/aaronartistzhang-afk/dailywork/skill-evolve-loop"><img src="https://agentmods.dev/badge/skills/aaronartistzhang-afk/dailywork/skill-evolve-loop.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 | $0.00186 | $0.01332 |
| Opus 5 | $0.00093 | $0.00666 |
| Sonnet 5 | $0.00037 | $0.00266 |
| Haiku 4.5 | $0.00019 | $0.00133 |
Grade A, and why
skill-evolve-loop 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 9d 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
skill-evolve-loop — sediment a lesson into a living skill, then prove you didn't break it
Editing a skill that already ships is not the same as writing one: you can break behavior that used to work, and another session may be mid-edit on the same file. This loop covers the edit path: fold one lesson in, run a five-class regression, backfill only what failed.
When this triggers
- The human says: "沉淀到 skill 里边" / "把这轮教训写进 skill" / "skill 更新了跑一轮验证" / "fold this lesson into the skill".
- Or: a deliverable just finalized and a lesson is worth keeping — propose the sedimentation round yourself; don't wait to be asked.
The five-class behavior test
After a skill edit, spin up N parallel subagents — one class each — produce a pass table, then backfill only the failed classes. The five class names come from a real user's verification design; the one-line criterion under each is this skill's operationalization:
| Class | Operational check | Example |
|---|---|---|
| Routing | New trigger words hit; old scenarios don't stop routing here | A "sediment this lesson" request routes to the edited skill; an unrelated request doesn't |
| Regression | Old behavior unchanged — same prompt against the pre-edit version gives the same result | A prompt that used to produce a 3-step flow still produces 3 steps |
| Discipline | The skill's hard constraints (gates, taboos) are still obeyed after the edit | A send-gate the skill mandates still blocks an unstamped send |
| Content | The newly-added content is itself correct — quotes match their sources, commands actually run | Every quotation grep -F-matches its cited source; every shell snippet runs |
| Gate-under-pressure | Under adversarial pressure the gate still holds, not just on the happy path | A crafted bypass attempt is still refused |
The flow (five steps)
- Locate the smallest section to change — one rule, one taboo row, one trigger line. Don't rewrite the skill.
- Propose the diff — show it and wait for confirmation. A shared skill is inherited by every future session; edits are propose-first.
- Run the five classes as isolated parallel subagents.
- Produce the pass table — one row per class, pass/fail, with evidence.
- Backfill only the failed classes; re-run until the table is clean.
What ships with it
1 file 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.
- 9d ago First seen · 63 lines · 186 tokens per session scan A 597a2f51078e
skill-evolve-loop is a skill published in the GitHub repository aaronartistzhang-afk/DailyWork (1 stars, last pushed 11d ago), licensed MIT. It adds 186 tokens to every session and 1,332 once invoked, about $0.0009 per session on Opus 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 2026-08-31.
Other skills, from other repositories
create-custom-grader
Use when converting an existing benchmark, rubric, verifier, task YAML/JSON, or domain check into SkillEvaluator BYOG/BYOT custom evaluation.
ab-test-generator
Generate A/B test variants for affiliate content. Triggers on: "create A/B test", "test my headline", "optimize my CTA", "generate variants", "split test ideas", "improve click-through rate", "test my landing page copy", "headline alternatives", "CTA variations", "which version is better", "optimize conversions"…
authoring-ci-workflows
Use when adding or editing a GitHub Actions workflow, composite action, or reusable workflow under .github/ — new CI jobs, triggers, matrices, checkout/clone tuning, action pinning, GitHub App token auth, concurrency groups, timeout-minutes, paths filters, caching, or runner choice. Covers PostHog's workflow-authoring…
debugging-mcp-analytics
Debug, support, and build PostHog MCP Analytics — product analytics for MCP servers (the @posthog/mcp and posthog.mcp SDKs plus the mcpanalytics product). Use when MCP analytics data looks wrong or missing ("events aren't showing", "intent clusters are empty", "sessions are missing", "per-tool numbers look wrong")…
qa-frontend
Internal PostHog developer frontend/browser QA skill. Use only when a PostHog developer explicitly asks to run frontend QA, browser-test a PR, verify a UI flow against the local PostHog stack, use qa-frontend, or QA current frontend changes with browser/runtime evidence. Do not use for generic code review, PR review…
creating-online-evaluations
Author continuously-running online evaluations in PostHog AI observability, grounded in real failure modes you've identified. Use when the user wants evaluations that automatically score new generations or whole traces going forward — "create an eval to catch X", "continuously check that responses do Y", "turn these…