audit-outcomes SKILL.md skillA
audit-outcomes from tomzx/agents is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add tomzx/agents/audit-outcomes@git:20261007.b35fc4bPins git:20261007.b35fc4b in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- tomzx/agents
- Path
skills/pdlc/skills/audit-outcomes/SKILL.md- Versions recorded
- 5
- Latest version
- git:20261007.b35fc4b, committed Oct 7, 2026
- First version recorded
- Aug 5, 2026
- Size
- 3,127 bytes
- Repository stars
- 12
- License
- MIT
Trace shipped product outcomes back to the original problem and metrics, PDLC's equivalent of backpropagation. Catches drift where the spec was built faithfully but stopped being the right thing.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# 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
1. 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.
2. Walk it in reverse, from `health-report.md` back to `problems.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?
…Read the whole file at its exact version.
How to install
mdr add tomzx/agents/audit-outcomes@sha256:75535752d8488768The line at the top of this page pins the label git:20261007.b35fc4b, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_tjua3ckro6pfdwjy)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Aug 5, 2026 and Oct 7, 2026, about one every 16 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261007.b35fc4b latest | 2026-10-07 | b35fc4b | 3,127 B | A | view · diff |
| git:20261005.8154ecd | 2026-10-05 | 8154ecd | 3,119 B | A | view · diff |
| git:20261004.00bb0c5 | 2026-10-04 | 00bb0c5 | 3,223 B | A | view · diff |
| git:20260921.1b27178 | 2026-09-21 | 1b27178 | 3,192 B | A | view · diff |
| git:20260805.6b62307 | 2026-08-05 | 6b62307 | 3,193 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (3127 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
tomzx/agents · 12 stars · license MIT · pushed 2026-10-21 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_tjua3ckro6pfdwjy GET https://markdownregistry.com/api/v1/resolve?ref=tomzx/agents/audit-outcomes GET https://markdownregistry.com/api/v1/blob/75535752d848876899b722271d47ad5b60e5b34e9b25d4ff3cabff2d6392e605
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.