run-slice SKILL.md skillA
run-slice from beakpoint-insights/roost is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add beakpoint-insights/roost/run-slice@git:20261026.505a1daPins git:20261026.505a1da in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- beakpoint-insights/roost
- Path
skills/run-slice/SKILL.md- Versions recorded
- 5
- Latest version
- git:20261026.505a1da, committed Oct 26, 2026
- First version recorded
- Oct 26, 2026
- Size
- 33,671 bytes
- Repository stars
- 30
- License
- MIT
Orchestrate one slice (story) from kickoff to done by driving the user's repo sessions (one Claude session per repo in the team's roost config, for example an API session and a UI session) over cross-session messages. Sends each repo's kickoff prompt from the tracker in order, has the stack's owner start the local stack, then loops through test verification, code review, fixes and exploratory testing, stopping for the user's decisions. Never edits any repo itself. Picks up where a stopped run…
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
# Run Slice
You coordinate. Other Claude sessions do the work, one per repo in the config's `repos` (for example the **API session** and the **UI session**). You never edit, build or run tests in any repo yourself. Everything happens through `SendMessage`.
**First, load the team config with `roost-config`.** This skill uses `repos`, `stack`, `tracker`, `tests`, `vcs`, `planning.review_focus` and `team.state_dir`. "Each repo, in order" means the `repos` list by `order`.
## Inputs
- **STORY:** the slice's ticket key.
- A session for each repo the story touches must already be open. If one isn't, ask the user to open it and stop.
Every run starts with **step R (resume check)**, even a first run, so stopping and restarting is always safe. Before step R's report, work out which roost you run ("Which roost is running" in `roost-config`) and say it in that report. Before sending any work, new or resumed, do **step 0** (find the sessions and check they run the same roost as you), even when step R picks up at a later step.
If the user only asks where things stand ("where are we on PROJ-X?", "what's left?"), use **Status** below and stop there.
## Status: "where are we?"
…Read the whole file at its exact version.
How to install
mdr add beakpoint-insights/roost/run-slice@sha256:135df48c96320e42The line at the top of this page pins the label git:20261026.505a1da, 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_uakpjfk2rhebiasv)
0 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, all committed on Oct 26, 2026.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261026.505a1da latest | 2026-10-26 | 505a1da | 33,671 B | A | view · diff |
| git:20261026.b78c131 | 2026-10-26 | b78c131 | 33,426 B | A | view · diff |
| git:20261026.dec76bc | 2026-10-26 | dec76bc | 33,304 B | A | view · diff |
| git:20261026.c517de3 | 2026-10-26 | c517de3 | 33,071 B | A | view · diff |
| git:20261026.66cdcd9 | 2026-10-26 | 66cdcd9 | 32,193 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 (33671 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
beakpoint-insights/roost · 30 stars · license MIT · pushed 2026-10-31 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_uakpjfk2rhebiasv GET https://markdownregistry.com/api/v1/resolve?ref=beakpoint-insights/roost/run-slice GET https://markdownregistry.com/api/v1/blob/135df48c96320e42f58012e4a9a23508be4f6c0fb562f30b6de8c1eef059244e
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.