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 CassioRoos/godfly-skills --skill incident-validatorgit clone --depth 1 https://github.com/CassioRoos/godfly-skillsWrote 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/cassioroos/godfly-skills/incident-validator)<a href="https://agentmods.dev/skills/cassioroos/godfly-skills/incident-validator"><img src="https://agentmods.dev/badge/skills/cassioroos/godfly-skills/incident-validator/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/cassioroos/godfly-skills/incident-validator"><img src="https://agentmods.dev/badge/skills/cassioroos/godfly-skills/incident-validator.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 | $0.00159 | $0.05237 |
| Opus 5 | $0.00079 | $0.02618 |
| Sonnet 5 | $0.00032 | $0.01047 |
| Haiku 4.5 | $0.00016 | $0.00524 |
Grade C, and why
incident-validator scanned grade C 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 today.
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.
Tells the agent never to refusehighAnti-refusal
Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.
Never silently validate against a stale copy. Never refuse to run because the live How it starts
The opening of the file, as written. The whole thing — 404 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Incident Validator
The standard says: "If exceptions become normal, the standard is fake." This skill is the mechanism that keeps it real. It validates incident artifacts against the Production Issue Resolution Standard -- not by checking that section headers exist, but by interrogating whether each requirement is actually satisfied, with evidence.
Tools: use Read/Grep/Glob/Bash (gh) plus whatever verification tools the session
has -- Linear MCP, Datadog MCP, Postgres MCP, WebFetch. Postgres is READ-ONLY here:
a validator never issues a mutation, whatever the connection permits. A missing tool
downgrades evidence strength (see the ladder); it never blocks the run. Report each
capability as unavailable | available-but-failed | unauthorized | not-attempted --
"no tool" must never quietly become an invented result.
The Source of Truth
The standard lives in the docs repo, NOT in this skill. Resolve it at the start of every run, in this order:
- Local checkout: look for
engineering/foundations/guides/production-issue-resolution-standard.mdunder a localdocsrepo checkout (glob for it near the working directory and in~/Documents/projects/*/docs). - GitHub fetch:
gh api -H "Accept: application/vnd.github.raw" repos/getalternative/docs/contents/engineering/foundations/guides/production-issue-resolution-standard.md - Embedded snapshot:
reference/standard-snapshot.mdin this skill -- use it ONLY as last resort, and open your output with a loud warning naming the snapshot date: "Validating against standard snapshot from -- could not reach the live version."
Never silently validate against a stale copy. Never refuse to run because the live
copy is unreachable. Derive the gates from whichever version you resolved; the
cookbook rubrics are the method, the standard is the law. Record what you resolved:
absolute path or fetched ref, plus commit SHA when gh supplied one.
All three rungs failed? Then there is no law to enforce, and that is terminal:
What ships with it
8 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.
- today Changed · +130 lines · +9 tokens per session 3216767f462f
- 8d ago First seen · 274 lines · 150 tokens per session scan C ced7f4ae69b6
incident-validator is a skill published in the GitHub repository CassioRoos/godfly-skills (1 stars, last pushed today), licensed MIT. It adds 159 tokens to every session and 5,237 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it C with 1 finding (tells the agent never to refuse). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
auto-test-code
A structured process for critically reviewing and testing software code. It records review findings, test plans, commands, results, and supporting files in a project workspace.
git-pr-review
A read-only reviewer for GitHub pull requests, which are proposed code changes submitted for review. It produces an evidence-based report about whether a pull request should be merged.
code-remediate
Apply selected review fixes; bare PR targets use current online items, while PR +review adds the latest matching artifact.
code-review
Close PRs at an evidence gate or review local diffs/PRs with specialists and JSON artifacts.
code-reviewer
A code-review workflow that checks completed work against its requirements or plan before merging. It groups findings by severity and gives each issue a fix and a way to verify it.
coding-assistant
Provides coding assistance with best practices and code review.