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 EZotoff/ez-omo-config --skill postmortem-policygit clone --depth 1 https://github.com/EZotoff/ez-omo-configWrote 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/ezotoff/ez-omo-config/postmortem-policy)<a href="https://agentmods.dev/skills/ezotoff/ez-omo-config/postmortem-policy"><img src="https://agentmods.dev/badge/skills/ezotoff/ez-omo-config/postmortem-policy/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/ezotoff/ez-omo-config/postmortem-policy"><img src="https://agentmods.dev/badge/skills/ezotoff/ez-omo-config/postmortem-policy.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 | $0.00055 | $0.00752 |
| Opus 5 | $0.00028 | $0.00376 |
| Sonnet 5 | $0.00011 | $0.00150 |
| Haiku 4.5 | $0.00006 | $0.00075 |
Grade A, and why
postmortem-policy 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 3d 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Postmortem → Policy
Triggers: /postmortem-policy, postmortem, incident review, "how do we prevent this", "falling into this seam again"
The acceptance boundary (non-negotiable)
You may research, analyze, draft, and queue. You may NOT apply any amendment — no file edit, no wisdom write, no skill change — until the operator explicitly approves the specific diff you show. Output always terminates in a decision checkpoint: apply / revise / drop.
Workflow
1. Accept the incident
Input: an incident description, a log excerpt, a session reference, or just "the thing that just broke". If input is vague, reconstruct from the current session's recent history before asking questions.
2. Root cause
Establish the causal chain to the earliest preventable link — the point where an instruction, skill, config, or convention, if it had existed or been followed, would have prevented the incident. Distinguish:
- agent error despite good instructions (no policy fix; note it),
- missing or ambiguous instruction (policy candidate),
- tooling gap no instruction can fix (escalate as infrastructure work, not policy).
3. Find the gap
Search where the fix would live, in this order:
- Project
AGENTS.mdfiles (repo root and~/.config/opencode/AGENTS.md) - Existing skills (
~/.config/opencode/skills/*/SKILL.md) - Wisdom store (
~/.sisyphus/scripts/wisdom-search.sh "<keywords>")
If a rule already exists and was ignored, the incident is an enforcement problem — say so; do not write a duplicate rule.
4. Propose the minimal amendment
Exactly one of:
- an
AGENTS.mdedit (show old → new lines, minimal delta), - a skill patch (file + section),
- a new wisdom entry (use
wisdom-write.shsemantics; show the entry text).
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.
- 3d ago First seen · 60 lines · 55 tokens per session scan A 41348d9e6292
postmortem-policy is a skill published in the GitHub repository EZotoff/ez-omo-config (5 stars, last pushed 4d ago), licensed MIT. It adds 55 tokens to every session and 752 once invoked, about $0.0003 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 2026-09-06.
Other skills, from other repositories
launch
Shipyard's governed delivery pipeline — converge the mission, synthesize a durable spec, decompose vertical-slice tickets with blocking edges, run the frontier in parallel via team, close with verification, and report with a full decision log. Two entry gates — the yard gate (drydock audit) and the fog gate (an effort…
omc-plan
Strategic planning with optional interview workflow.
ralph
Self-referential loop until task completion with configurable verification reviewer.
self-improve
Autonomous evolutionary code improvement engine with tournament selection.
autopilot
Full autonomous execution from idea to working code.
drydock
Lay the keel of the shipyard harness in any repo — the 4-pillar shared environment (Context, Rules, Tools, Standards) across 5 surfaces (CLAUDE.md, skills, design-system, mcp/cli, shared context) so that every human and agent inherits the same design language and anyone can ship. Run once per repo; re-run with --check…