coordinator-discipline

coordinator-discipline is a skill for Claude Code, Codex from ashfulcra/fulcra-tools. It costs 47 tokens per session (1,937 once invoked), scanned A, original, MIT.

A set of checklists for coordinating work done by multiple coding agents. It tells the coordinator when to verify evidence, message details, merge changes, dispatch work, and claim completion.

In plain words
What is it for?
Use it to review agent findings, confirm approvals, check merge evidence, and decide whether multi-agent work is genuinely complete.
Why use it?
It reduces mistakes caused by trusting unverified reports, acting on incomplete messages, merging outdated work, or treating silence as success.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to review agent findings, confirm approvals, check merge evidence, and decide whether multi-agent work is genuinely complete.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ashfulcra/fulcra-tools/coordinator-discipline
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add ashfulcra/fulcra-tools --skill coordinator-discipline
Clone the repo
git clone --depth 1 https://github.com/ashfulcra/fulcra-tools

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for coordinator-discipline

README.md
[![agentmods](https://agentmods.dev/badge/skills/ashfulcra/fulcra-tools/coordinator-discipline/github.svg)](https://agentmods.dev/skills/ashfulcra/fulcra-tools/coordinator-discipline)
Your own site
<a href="https://agentmods.dev/skills/ashfulcra/fulcra-tools/coordinator-discipline"><img src="https://agentmods.dev/badge/skills/ashfulcra/fulcra-tools/coordinator-discipline/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for coordinator-discipline

Your own site · 80×15
<a href="https://agentmods.dev/skills/ashfulcra/fulcra-tools/coordinator-discipline"><img src="https://agentmods.dev/badge/skills/ashfulcra/fulcra-tools/coordinator-discipline.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,937 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00047 $0.01937
Opus 5 $0.00023 $0.00968
Sonnet 5 $0.00009 $0.00387
Haiku 4.5 $0.00005 $0.00194

Measured 9d ago against content hash 923acd53d3e5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

coordinator-discipline scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/coordinator-discipline/SKILL.md · 148 lines

How it starts

The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Coordinator discipline

A coordinator's failures are rarely exotic. They are ordinary claims believed without verification, ordinary messages sent without bodies, ordinary merges performed on evidence that moved, and ordinary silences read as success. Every gate below was earned by a real incident of exactly that shape. The skill is organized as gates: before you take the named action, walk its checklist.

Gate 1 — BEFORE RULING on anything

  1. Verify the load-bearing claim yourself. Re-run the grep, read the code at the cited line, fetch the exact artifact. A report's conclusion is input, not evidence. (Incident: a "defined and never called" claim that a one-line grep disproved — the pattern matched the path literal while the callers used a helper.)
  2. Never rule on a title. If the thing you are ruling on arrived as a slug, a subject line, or a summary, fetch the body first. Refuse — loudly — to act on obligation-changing messages that have no body, and honor the same refusal from others.
  3. Relayed authorization carries provenance, verbatim. When you relay a human's decision, quote their exact words and say where and when they said them. "Should be in your channel now" when you mean "I told them to" is an inference recorded as fact — the class of error that poisons trust in every later relay.
  4. When someone falsifies your framing, say so in the ruling. Adopt the corrected frame by name and withdraw the dead one explicitly, so the record never carries two live framings.

Gate 2 — BEFORE MERGING reviewed work

  1. Approval binds to one immutable artifact identity, checked across every authoritative source at merge time. Whatever your stack's identity is — a commit sha, a content hash, a version id — the identity that was approved, the identity the review system holds, and the identity you are about to publish must be byte-identical. ANY change produces a new identity and needs a new round: even a trivial conflict resolution can carry a defect under an honest approval. (Git realization: approved head == PR head == remote branch tip.)
  2. A squash or rebase on a dependency destroys ancestry for stacked branches; their prior approvals die with it. Re-round, don't rationalize.
  3. Closure carries evidence. The settle record written after a merge carries the merge sha, the approved head, who merged, and when. "Settled" without a sha is a tally cache, not merge evidence — and anything that can recompute a cache can silently replace evidence unless the writer refuses to overwrite the stronger state with the weaker.
  4. Read back what you wrote. A closure marker that was never re-fetched may have lost a race you did not know was running.

Read the full file on GitHub · 148 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 148 lines · 47 tokens per session scan A 923acd53d3e5

Subscribe to this mod's changes

coordinator-discipline is a skill published in the GitHub repository ashfulcra/fulcra-tools (10 stars, last pushed yesterday), licensed MIT. It adds 47 tokens to every session and 1,937 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.