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.
npx skills add ashfulcra/fulcra-tools --skill coordinator-disciplinegit clone --depth 1 https://github.com/ashfulcra/fulcra-toolsWrote 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.
[](https://agentmods.dev/skills/ashfulcra/fulcra-tools/coordinator-discipline)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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
- 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.)
- 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.
- 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.
- 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
- 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.)
- A squash or rebase on a dependency destroys ancestry for stacked branches; their prior approvals die with it. Re-round, don't rationalize.
- 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.
- Read back what you wrote. A closure marker that was never re-fetched may have lost a race you did not know was running.
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.
- 9d ago First seen · 148 lines · 47 tokens per session scan A 923acd53d3e5
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.
Other skills, from other repositories
magic-compact
Compact this Claude Code session.
citation-intelligence
Use when the user wants to know which URLs AI engines cite for a query, whether their domain is being cited by ChatGPT/Claude/Perplexity/Gemini/Google AI Overviews/Bing, what queries their site is cited for, how citation rate changes over time, or how their citation coverage compares to competitors. Self-hosted, BYO…
proof-engine
Create formal, verifiable proofs of claims with machine-checkable reasoning. Use when asked to prove, verify, fact-check, or rigorously establish whether a claim is true or false — mathematical, empirical, or mixed. Trigger phrases: "is it really true", "can you prove", "verify this", "fact-check this", "prove it"…
join
Join the Cortex agent team — reads agent config from team directory, generates .cortex.md protocol, updates CLAUDE.local.md. Idempotent — safe to re-run as a sync.
setup
First-time Cortex setup — creates team directory, config, and chief of staff agent.
leave
Leave the Cortex agent team — removes .cortex.md, cleans CLAUDE.local.md, sets agent status to inactive in team directory.