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 Eliyce/paqad-ai --skill finding-normalizergit clone --depth 1 https://github.com/Eliyce/paqad-aiWrote 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/eliyce/paqad-ai/finding-normalizer)<a href="https://agentmods.dev/skills/eliyce/paqad-ai/finding-normalizer"><img src="https://agentmods.dev/badge/skills/eliyce/paqad-ai/finding-normalizer.svg" alt="Measured on agentmods" 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 | $0.00015 | $0.00780 |
| Opus 5 | $0.00008 | $0.00390 |
| Sonnet 5 | $0.00003 | $0.00156 |
| Haiku 4.5 | $0.00002 | $0.00078 |
Grade A, and why
finding-normalizer 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 8d 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
What It Does
Normalizes evidence from docs, tests, runtime checks, and advisory feeds into stable finding entries with consistent ids, severity, effort, and reproduction data.
Finding-id prefixes recognised by the normalizer are listed under # code-prefix in assets/vocabulary.txt:
PEN-*— pentest findings (security workflow).DT-*— design-test findings (design-system audit workflow; issue #76). Categories:token | component | state | a11y | responsive | motion | copy | performance | documentation-drift.tokenfindings default to high severity to surface hard-coded design values (hex literals, raw px/rem, ad-hoc font stacks where a token exists).SM-*— site-map findings (site-map / site-map-retest workflow;docs/site-map/<ts>.json). The id is a content-addressedSM-<hash8>; theSM-ADD | SM-REMOVE | SM-EDGE-STALE | SM-GUARD-DRIFT | SM-JOURNEY-BROKEN | …names arecategoryvalues, listed under# site-map categoryinassets/vocabulary.txt.MD-*— prospective module decisions (issue #80, Phase 1). Stored under.paqad/decisions/module-decisions/<id>.yml; the consumer is the Attribution Gate, not the pentest workflow. Treat severity/effort/status as advisory only forMD-*— the binding state machine lives insrc/module-decisions/schema.ts.
Use This When
Use this after raw security evidence has been collected and needs to be turned into report-ready findings or retest statuses.
Inputs
- Read the structured evidence payload first.
- Read
references/finding-fields.mdbefore setting severity or effort. - Read retest state when the workflow is
pentest-retest.
Procedure
- Deduplicate findings that describe the same risk surface.
- Pick severity, effort, and status from the closed sets in
assets/vocabulary.txt. - Preserve ids and prior statuses when normalizing retest output.
- Format the JSON exactly per
assets/output.template.json. - Validate with
scripts/validate-findings.sh— checks required fields, vocabulary, and id uniqueness.
What ships with it
5 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.
- 8d ago First seen · 71 lines · 15 tokens per session scan A 9aa5fa0aa6d6
finding-normalizer is a skill published in the GitHub repository Eliyce/paqad-ai (8 stars, last pushed today), licensed MIT. It adds 15 tokens to every session and 780 once invoked, about $0.0001 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
pr-writing-review
Extract and analyze writing improvements from GitHub PR review comments. Use when asked to show review feedback, style changes, or editorial improvements from a GitHub pull request URL. Handles both explicit suggestions and plain text feedback. Produces structured output comparing original phrasing with reviewer…
session-investigator
Investigate fast-agent session and history files to diagnose issues. Use when a session ended unexpectedly, when debugging tool loops, when correlating sub-agent traces with main sessions, or when analyzing conversation flow and timing. Covers session.json metadata, history JSON format, message structure, tool…
auto-go
A command that implements code from a SPEC, a document describing the required behavior and work.
auto-plan
A code-planning skill that examines a codebase and creates a detailed specification, implementation plan, and acceptance criteria. It can organize requirements using EARS, a structured way to describe how software should behave in different situations.
agent-pipeline
Multi-agent pipeline orchestration skill.
adaptive-quality
Per-task execution profile selection based on complexity in Balanced quality mode.