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 tomzx/agents --skill audit-outcomesgit clone --depth 1 https://github.com/tomzx/agentsWrote 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/tomzx/agents/audit-outcomes)<a href="https://agentmods.dev/skills/tomzx/agents/audit-outcomes"><img src="https://agentmods.dev/badge/skills/tomzx/agents/audit-outcomes/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/tomzx/agents/audit-outcomes"><img src="https://agentmods.dev/badge/skills/tomzx/agents/audit-outcomes.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 | $0.00041 | $0.00731 |
| Opus 5.5 | $0.00016 | $0.00292 |
| Sonnet 5.5 | $0.00008 | $0.00146 |
| Haiku 4.5 | $0.00004 | $0.00073 |
Grade A, and why
audit-outcomes 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 22d 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Audit Outcomes
Walks the PDLC artifact chain in reverse to verify traceability from start to finish: does what shipped trace to a validated opportunity, and do the health metrics justify the original decision?
This is the PDLC equivalent of propagate-changes, but it judges outcome coherence, not spec-to-code consistency.
Prerequisites
- Apply the shared PDLC conventions in
skills/pdlc/references/shared.md. - A shipped or measured initiative (
$1), or scan all initiatives under.pdlc/initiatives/.
Steps
- For the target initiative, gather the chain:
opportunity-tree.md→experiment-result.md→prd.md→acceptance-contract.md→health-report.md→feedback-loop.md, plus all decision records. - Walk it in reverse, from
health-report.mdback toproblems.md, checking each link:- Do the measured outcomes map back to the success metrics defined in
prd.md/analytics-spec.md? - Were guardrail metrics defined up front and checked after launch? (A missing guardrail is itself a finding.)
- Does the shipped scope trace to the acceptance contract, which traces to the PRD outcomes, which trace to a validated opportunity?
- Does each gate decision still look defensible when reviewed later?
- Do the measured outcomes map back to the success metrics defined in
- Score each link
aligned/drifted/broken. A link isdriftedwhen the artifact evolved without updating the chain;brokenwhen the outcome contradicts the premise. - For any
driftedorbrokenlink, regress the relevant gate decision topivot(record in a new decision record) so the forward loop resyncs it. - Produce the audit report.
Findings Categories
- Traceability gaps — a shipped outcome with no upstream opportunity, or an opportunity with no measured outcome.
- Metric drift — success metrics changed without re-validating the opportunity; guardrails missing or unmeasured.
- Decision rot — a gate decision that no longer holds given new evidence.
- Premature shipping — launched before the gate chain was complete.
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.
- 22d ago Changed · +3 lines 75535752d848
- 23d ago Changed · -4 lines 1ddbc7cc9fa2
- 24d ago Changed 4856d68bd386
- 1mo ago Changed 91f333e299b1
- 1mo ago First seen · 66 lines · 41 tokens per session scan A 1b89d09c5e53
audit-outcomes is a skill published in the GitHub repository tomzx/agents (13 stars, last pushed yesterday), licensed MIT. It adds 41 tokens to every session and 731 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…