outcome-check SKILL.md skillA
outcome-check from sara-star-quant/presence is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add sara-star-quant/presence/outcome-check@git:20260426.243df5aPins git:20260426.243df5a in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- sara-star-quant/presence
- Path
skills/outcome-check/SKILL.md- Versions recorded
- 1
- Latest version
- git:20260426.243df5a, committed Apr 26, 2026
- Size
- 2,405 bytes
- Repository stars
- 8
- License
- Apache-2.0
When you're about to claim a previous fix worked, or are tempted to repeat an approach Claude Code has tried in this repo before, consult the outcome telemetry. presence tracks every commit Claude made and watches for reverts. Look up "did my last attempt at X stick?" before re-trying.
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
# Outcome check: learn from your own past
`presence` records every commit you make (`~/.claude/presence/telemetry/claims.jsonl`) and scans for reverts in subsequent sessions (`outcomes.jsonl`). When you're about to do something you've done before in this repo, **check first whether it worked**.
## When this skill should fire
- You're about to fix a bug in a file you've previously fixed.
- You're proposing an architectural change you suspect was tried before.
- A user asks "didn't you fix this?" or "this looks familiar."
- You're about to commit something with a message similar to an earlier commit.
## How to consult
```bash
PRESENCE_ROOT="${CLAUDE_PLUGIN_ROOT:-$(realpath ~/.claude/plugins/presence 2>/dev/null || echo .)}"
PYTHONPATH="$PRESENCE_ROOT/lib" python3 -c "
from _common import read_jsonl, repo_id
from telemetry import claims_path, outcomes_path
rid = repo_id('$PWD')
claims = [c for c in read_jsonl(claims_path()) if c.get('repo') == rid]
outcomes = read_jsonl(outcomes_path())
reverted_shas = {o['sha'] for o in outcomes if o.get('kind') == 'revert'}
for c in claims[-20:]:
sha = c.get('sha', '?')[:8]
msg = (c.get('message') or '')[:80]
…Read the whole file at its exact version.
How to install
mdr add sara-star-quant/presence/outcome-check@sha256:89e10d49b0b6facfThe line at the top of this page pins the label git:20260426.243df5a, 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_6eoztpval54uiu5g)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Apr 26, 2026.
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 (2405 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
sara-star-quant/presence · 8 stars · license Apache-2.0 · pushed 2026-10-30 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_6eoztpval54uiu5g GET https://markdownregistry.com/api/v1/resolve?ref=sara-star-quant/presence/outcome-check GET https://markdownregistry.com/api/v1/blob/89e10d49b0b6facf04e33bdd47a8fc4765fea4c1249ede83823bacfbffff509c
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.