agentleFS
Sign inStart free
EONRaiderEONRaider/agent-router/skills/report/SKILL.md

report

Skill0 starsChanged 40 days agoMITView on GitHub

Show the agent-router report for the current project (spawns, problems and estimated spend per tier) and walk the user through its proposals, accepting or rejecting each one. Use when the user runs /agent-router:report, asks how the routing tiers are performing, asks whether a tier should be resized, or wants to review agent-router proposals. With the argument "print" it only prints the report; with "group" it also groups similar briefs.

93 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use opportunities, export and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • ansvisorSkill

    opportunities

    Finds content gaps, prompts worth tracking, and the off-site sources AI cites instead of the brand.

    Also in 3 projects that use this

  • soilmassSkill

    export

    Animation export configurations including format selection, resolution, framerate, quality, and optimization settings. Use when rendering animations for web, mobile, video, or social media. Provides tokens for all export parameters across Lottie, GIF, video, and sprite sheet formats.

    Also in 4 projects that use this

  • GoogleSkill

    quality

    Evaluates whether a GitHub issue is spam, empty, needs more information, or is OK to proceed.

    Also in 3 projects that use this

  • genomewalkerSkill

    resume

    Resume a thread by loading its ~800-token context capsule

    Also in 7 projects that use this

  • tokyubevoxelverseSkill

    checkup

    Give a repository a full health exam — doc rot, dependency staleness, CI decay, git hygiene, dead links, docs contradicting code — and grade it. Use when the user wants to know what quietly rotted, or a prioritized maintenance list.

    Also in 3 projects that use this

  • rajnavakotiSkill

    scan

    Run the AI dashboard scanner and generate the HTML report.

    Also in 5 projects that use this

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 68 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

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

    If the argument is print, stop here.

    line 21

“Common” is measured: kept by at least 6 in 10 of the 68 edited versions of this file we could read. “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

agent-router report

The plugin never changes its own configuration. Every proposal is accepted or rejected by the user. Do not accept one on their behalf, and do not edit .claude/agent-router.json by hand to apply one.

1. Run the report

python3 "${CLAUDE_PLUGIN_ROOT}/scripts/router.py" report

Show the user the tier lines and the proposals. Say plainly that the signals are proxies: "not redone" is not "good", and estimated spend uses list prices on logged tokens.

If the argument is print, stop here.

2. Decide each proposal

For each proposal, ask the user with AskUserQuestion: accept or reject. Put the evidence and the overlay edit in the question so the choice is informed. Then record the choice:

python3 "${CLAUDE_PLUGIN_ROOT}/scripts/router.py" decide <proposal-id> accept
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/router.py" decide <proposal-id> reject
  • Accepting edits .claude/agent-router.json, regenerates the project agents and records the decision. Nothing is committed: tell the user the changed files so they can review and commit them. A resized or added tier loads in the next session.
  • Rejecting records the decision. The proposal stays quiet until new evidence, on its own, meets the threshold again.
  • A downgrade is a trial. Later reports judge it on the spawns made since it started and propose reverting it if the tier starts being redone.
  • A proposal with no overlay edit (a shared preamble) needs work by hand; relay its instructions and do not record a decision unless the user rejects it.

3. Grouping similar briefs (only for group)

The rules count exact matches. To see whether overrides or rejections cluster around one kind of task, run:

python3 "${CLAUDE_PLUGIN_ROOT}/scripts/router.py" report --summaries

Group the summaries yourself by kind of task and tell the user which groups recur and what that suggests (a project tier, a phrase to drop, a specialised agent). This step only informs; it produces no automatic edit. Run it when asked, not on every report.

Scheduling

To run the report on a schedule, the user can schedule /agent-router:report print. The scheduled run prints the report; proposals still wait for a person.

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