agentleFS
Sign inStart free
fws94fws94/product9-token-saver/skills/batch-status/SKILL.md

batch-status

Skill1 starsChanged 56 days agoMITView on GitHub

Use when collecting read-only status for several known GitHub pull requests, GitLab merge requests or Linear issues.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read data.rows in requested order.

    line 26
  2. Very specific:

    Check states are success, failure, pending or unknown.

    line 30

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Batch status

For GitHub, use the deterministic helper only after the parent identifies the exact OWNER/REPO and PR numbers. It uses the existing authenticated gh CLI; no token, account, provider or schedule is inferred. For GitLab and Linear, follow the host-tool route using tools already available to the parent. The CLI does not accept those providers; do not claim an executable adapter before a target environment is verified.

python scripts/token_saver.py status --provider github --repo OWNER/REPO --prs 11 12 13 --max-concurrency 4

The command performs one gh pr view NUMBER --repo OWNER/REPO --json number,url,state,statusCheckRollup per unique number, with a bounded thread pool. It is read-only: never change the command into edit, comment, merge, or another write operation. Duplicate input numbers are reported once in input order. A positive concurrency bound is required by the helper and defaults to 4.

Read data.rows in requested order. GitHub rows have a PR identifier, number, URL, normalized state and check summary. For host-tool GitLab/Linear queries, retain each provider's identifier and state without pretending the GitHub CLI returned them; use the shared envelope statuses and check-state vocabulary. Check states are success, failure, pending or unknown; an empty rollup is unknown. Classify other checks from observed status and conclusion fields. A row error is preserved with a bounded kind/message. Permission errors are unknown access, not proof that the target does not exist.

Interpret the envelope separately from source state: top-level completed means all targets were read, even when a PR state is CLOSED or its checks failed. partial means at least one target could not be read after a provider tool was available, even if every attempted read failed; blocked means no target can be queried because the GitHub CLI is unavailable, or because a GitLab/Linear host read tool or exact project/workspace identity is unavailable. Do not retry an inaccessible target or create a scheduled monitor automatically. Return provider errors and substantive status interpretation to the parent.

See batch-status behavior and the result contract.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free