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 bikeread/promethos --skill turn-postmortem-to-improvementgit clone --depth 1 https://github.com/bikeread/promethosWrote 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/bikeread/promethos/turn-postmortem-to-improvement)<a href="https://agentmods.dev/skills/bikeread/promethos/turn-postmortem-to-improvement"><img src="https://agentmods.dev/badge/skills/bikeread/promethos/turn-postmortem-to-improvement/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/bikeread/promethos/turn-postmortem-to-improvement"><img src="https://agentmods.dev/badge/skills/bikeread/promethos/turn-postmortem-to-improvement.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 | $0.00034 | $0.00663 |
| Opus 5.5 | $0.00014 | $0.00265 |
| Sonnet 5.5 | $0.00007 | $0.00133 |
| Haiku 4.5 | $0.00003 | $0.00066 |
Grade A, and why
turn-postmortem-to-improvement 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 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.
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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Goal
Convert isolated experience into a reusable improvement to the skills library or evaluation stack.
Inputs
- Incident transcript, bug, or success case
- Root cause or corrective discussion
- Current related skills and evals
Non-Goals
- Writing a blame document
- Creating a new skill before understanding the actual pattern
Workflow
Trigger signals
- A bug was just fixed and user asks "怎么防止再犯" or "how do we prevent this"
- A debugging session ended with a confirmed root cause
- An unexpectedly smooth workflow deserves capture before context is lost
- Not for drafting the final skill once the remediation layer is already chosen
1. Capture the incident or success as evidence
Record what triggered the situation, what the agent tried to do, what happened, and which details actually mattered to the outcome. Include enough context that someone else could recognize the same pattern later. Success criteria: The event is written as a concrete case with observable facts, not as a vague lesson.
2. Identify the real failure or success pattern
Strip away the surface symptoms and name the reusable pattern underneath: a bad assumption, a missing guardrail, an eval gap, a workflow win, or a skill boundary that should change. Separate one-off noise from behavior that is likely to repeat. Success criteria: The root pattern is clear enough to justify a reusable change, or the incident is correctly classified as non-repeatable.
3. Choose the lightest effective remediation layer
Decide whether the fix belongs in an existing skill, a new skill, a guardrail, an evaluation, a plan template, or a simple rule or reference update. Prefer the smallest change that will actually stop the recurrence or preserve the useful pattern. Success criteria: The proposed remedy matches the real failure mode and is no larger than necessary.
4. Draft the reusable update and follow-up check
Write the concrete change, including what will be added, revised, removed, or tested next. If the update affects behavior, note how it should be verified later. Success criteria: The change is actionable, tied to the pattern, and has a clear next check or follow-through step.
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 · 78 lines · 34 tokens per session scan A 3c57eb10d641
turn-postmortem-to-improvement is a skill published in the GitHub repository bikeread/promethos (33 stars, last pushed 7mo ago), licensed MIT. It adds 34 tokens to every session and 663 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-30.
turn-postmortem-to-improvement compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| turn-postmortem-to-improvementbikeread/promethos | Skill | 33 | 7mo ago | MIT | A | 34 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 103 | Claude Code |