Skip to content
Agentmart
Submit a tool

report-run

Use when recording Involute run progress — running, blocked, or completed.

Skill by fakechris

IndexedApache-2.0★ 1
Write a review

Chalk Labs

Need help deploying report-run?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/fakechris-report-run

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Use when recording Involute run progress — running, blocked, or completed. Completed runs go to In Review; agents never Done.

Use cases: documents

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md and code. Checked Nov 1, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/report-run

What's inside

Skill name
report-run
Description
Use when recording Involute run progress — running, blocked, or completed. Completed runs go to In Review; agents never Done.
License
Apache-2.0
Instructions
26 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Report run

Tool: `run_report`

## When

Starting work, hitting a blocker, or finishing a claim.

## How

- `work_id` + `status` (`running` | `blocked` | `completed`) + short `phase` / `summary`.
- `completed` also says what the run leaves behind (INV-1231): `followups: { work_ids: ["INV-123"] }` for work it led to — propose or file it first; each is linked DISCOVERED_DURING — or `followups: { none_reason: "..." }`. Missing: a warning until 2026-11-17, refused after. CLI: `--followups INV-1,INV-2` or `--none-left "..."`.
- Use `idempotency_key` for safe retries.
- Reuse `run_id` when continuing the same run.
- **No secrets** in summaries.

## Rules

- Completed → In Review. Never move work to Done yourself.
- Do not substitute chat comments for run reports.
- Blocked summaries must name the missing human/input path.

## Declined findings (INV-1432)

A receipt records what you did and why. It must also record what review asked for that you did **not** do — otherwise "why wasn't X handled?" can only be answered from a PR thread or a chat log, if at all.

When a `completed` run went through any review (local codex, PR bots, a person), `receipt.reasoning` lists every finding you declined or deferred, one per line:

- **source** — who raised it (e.g. `codex r2`, `coderabbit #515:491`, a person's handle);
- **finding** — one-line summary;
- **reason** — why not now (out of scope, pre-existing, cost exceeds the stake, disagree because …);
- **where it went** — a new `INV-n`, `won't do`, or `answered in the PR`.

If nothing was declined, write `Declined findings: none.` Fixed findings need no entry here; the commits and PR already show them. A deferral that needs follow-up gets its own item first, and the receipt names it.

## Execution ownership (INV-943)

`work_claim` returns a secret `claim_token` and an `executionId`. Keep the token in this execution’s secret state; never put it in a comment, receipt, log or Git. Pass `claim_token` when renewing the lease, reporting a run, attaching evidence, releasing your claim (`work_claim_release`, with a reason), or retracting your own pre-acceptance evidence (`evidence_retract`, with a reason). Sharing an actor identity does not share execution authority. After lease expiry, acquire a new claim and use its new token; old runs cannot resume. A lost token cannot be recovered from context: wait for expiry or ask a person to release the claim in the UI. Completed runs retain their token binding for attaching evidence after completion.

From fakechris/Involute, Apache-2.0.

More from fakechris/Involute

Signals

Stars
1
Forks
0
Open issues
0
Last commit (this folder)
Oct 2, 2026 (1 month ago)

From GitHub (fetched Oct 24, 2026).

Details

License
Apache-2.0
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from fakechris

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get report-run running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying report-run?

CallGet help
Cite this page

report-run skill. Agent Mart. https://agentmart.dev/skills/fakechris-report-run (last updated 2026-10-24)