oss-scouting SKILL.md skillA

oss-scouting from fabiandistler/agents is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add fabiandistler/agents/oss-scouting@v1.3

Pins v1.3 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
fabiandistler/agents
Path
skills/oss-scouting/SKILL.md
Versions recorded
5
Latest version
v1.3, committed Oct 23, 2026
First version recorded
Oct 17, 2026
Size
16,239 bytes
Repository stars
2
License
none declared

Scout one third-party open-source repository for open issues that suit a small, clean contribution, and write repro, root-cause analysis, fix diff, test, and a submit checklist to a local folder only.

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

# OSS Scouting

One run = one library. The result is analysis and drafts in a local folder that
the user fully understands, tests themselves, and submits under their own name.

## When to use

Use this on a request to scout a specific upstream project for contribution
candidates — "scouting run for `<lib>`", "find me issues in `<lib>`", "where
could I contribute to `<lib>`", "candidates for a PR to `<lib>`".

Not for maintaining the user's own repositories, not for debugging their own
code, and not for submitting anything — submission is exclusively the user's
job.

## Non-negotiable rules

1. **Local only.** No fork, no push, no PR, no issue comment, no reaction, no
   new issue. A read-only clone into a throwaway cache folder is allowed.
2. **Policy before search.** If the project rejects AI-assisted contributions,
   the run ends with a report — without reviewing a single issue.
3. **Quality over count.** At most 3 candidates. Zero candidates is a valid
   result and is reported as one. The `good first issue` label is neutral, not
   a filter. Respect reservations: where the project assigns such issues on
   request, ask to be assigned before working one up.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add fabiandistler/agents/oss-scouting@sha256:fe3b6e1887fd5cd8

The line at the top of this page pins the label v1.3, 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.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_ldkc3hjcojlc3ndq.svg)](https://markdownregistry.com/a/art_ldkc3hjcojlc3ndq)

0 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 5 versions of this file, between Oct 17, 2026 and Oct 23, 2026, about one every 2 days.

versioncommittedcommitsizeaudit
v1.3 latest2026-10-23 2374a31 16,239 BA view · diff
v1.32026-10-22 471aaec 16,183 BA view · diff
v1.32026-10-21 bda4a0b 16,185 BA view · diff
v1.32026-10-17 0ae3399 16,046 BA view · diff
v1.32026-10-17 187bcdf 16,044 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (16239 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

GitHub

fabiandistler/agents · 2 stars · license none declared · pushed 2026-11-01 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_ldkc3hjcojlc3ndq
GET https://markdownregistry.com/api/v1/resolve?ref=fabiandistler/agents/oss-scouting
GET https://markdownregistry.com/api/v1/blob/fe3b6e1887fd5cd8832e1adc651213977f9109c37fbb78220f95a7ed0f1e531f

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.

More from fabiandistler/agents

chief-of-staff SKILL.md skill
fabiandistler/agents · .claude/skills/chief-of-staff/SKILL.md · Pursue a long-running goal in a single session by co-ordinating subagents.
git:20261020.384aec7 · audit A · 2 stars
code-review SKILL.md skill
fabiandistler/agents · .claude/skills/code-review/SKILL.md · Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes: Standards (does the code…
git:20261013.8a329a6 · audit A · 2 stars
codebase-design SKILL.md skill
fabiandistler/agents · .claude/skills/codebase-design/SKILL.md · Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find…
git:20260930.0a9e31d · audit A · 2 stars
diagnosing-bugs SKILL.md skill
fabiandistler/agents · .claude/skills/diagnosing-bugs/SKILL.md · Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports…
git:20261013.8a329a6 · audit A · 2 stars
domain-modeling SKILL.md skill
fabiandistler/agents · .claude/skills/domain-modeling/SKILL.md · Build and sharpen a project's domain model. Use when discussing codebase terminology, writing or editing a GLOSSARY.md…
git:20260930.0a9e31d · audit A · 2 stars
grill-me SKILL.md skill
fabiandistler/agents · .claude/skills/grill-me/SKILL.md · A relentless interview to sharpen a plan or design.
git:20260930.0a9e31d · audit B · 2 stars
grill-with-docs SKILL.md skill
fabiandistler/agents · .claude/skills/grill-with-docs/SKILL.md · A relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.
git:20260930.0a9e31d · audit A · 2 stars
grilling SKILL.md skill
fabiandistler/agents · .claude/skills/grilling/SKILL.md · Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or…
git:20261013.8a329a6 · audit A · 2 stars
handoff SKILL.md skill
fabiandistler/agents · .claude/skills/handoff/SKILL.md · Compact the current conversation into a handoff document for another agent to pick up.
git:20261013.8a329a6 · audit A · 2 stars
implement-spec SKILL.md skill
fabiandistler/agents · .claude/skills/implement-spec/SKILL.md · Implement the result of /to-spec and /to-tickets in code.
git:20260930.0a9e31d · audit A · 2 stars
implement SKILL.md skill
fabiandistler/agents · .claude/skills/implement/SKILL.md · Implement a piece of work based on a spec or set of tickets.
git:20261013.8a329a6 · audit A · 2 stars
pr SKILL.md skill
fabiandistler/agents · .claude/skills/pr/SKILL.md · Use when writing a PR body.
git:20260930.0a9e31d · audit A · 2 stars

Every file in fabiandistler/agents

Browse by kind, by grade A, or by owner.