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 agentmods add agents/cveralyon/axel-setup/excelsior-coordinatorgit clone --depth 1 https://github.com/cveralyon/axel-setupWrote 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/agents/cveralyon/axel-setup/excelsior-coordinator)<a href="https://agentmods.dev/agents/cveralyon/axel-setup/excelsior-coordinator"><img src="https://agentmods.dev/badge/agents/cveralyon/axel-setup/excelsior-coordinator.svg" alt="Measured on agentmods" 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 | $0.00035 | $0.00561 |
| Opus 5 | $0.00017 | $0.00280 |
| Sonnet 5 | $0.00007 | $0.00112 |
| Haiku 4.5 | $0.00003 | $0.00056 |
Grade A, and why
excelsior-coordinator 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 5d 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Excelsior Coordinator Protocol
This is a reference protocol, not an agent to spawn. The main Claude instance IS the coordinator. Use this pattern when tasks are complex enough to require parallel research, implementation workers, and verification.
When to Activate
Activate coordinator mode when the task involves:
- Changes across 5+ files
- Multiple concerns (API + frontend + DB + tests)
- Cross-repo coordination
- Architecture decisions requiring research first
- Bug investigation spanning multiple systems
The 4 Phases
Phase 1: Research (PARALLEL)
Launch Explore agents in parallel to investigate the codebase:
// Launch in parallel — multiple Agent calls in one response
Agent({ subagent_type: "Explore", prompt: "Find all files related to X..." })
Agent({ subagent_type: "Explore", prompt: "How does Y work in this codebase..." })
Phase 2: Synthesis (YOU — the coordinator)
This is YOUR job. Not a worker's. You have context from all research threads.
Write a precise implementation spec:
- Exact files to create/modify
- What each change does and why
- Edge cases to handle
- Tests to write
- Order of operations
Share the spec with the user for alignment if the task is large.
Phase 3: Implementation (SEQUENTIAL or PARALLEL workers)
Launch general-purpose agents with precise specs:
Agent({ description: "Implement rate limiting", prompt: "..." })
Concurrency:
- Read-only → parallel
- Writes on different files → parallel OK
- Writes on same files → sequential
- One worker per commit scope
Phase 4: Verification (AUTOMATIC)
After implementation, ALWAYS spawn excelsior-verifier:
Agent({ subagent_type: "excelsior-verifier", run_in_background: true,
prompt: "Verify: [files], [changes], [expected behavior]" })
The verifier's verdict is final. On FAIL: fix and re-verify. On PASS: report to user.
Proactive Resolution
When workers hit obstacles:
- Don't ask the user — investigate and resolve
- Docker/services down → start them
- Deps missing → install them
- Tests fail → read errors, fix root cause
- Unclear requirement → research the codebase for existing patterns
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.
- 5d ago First seen · 76 lines · 35 tokens per session scan A 35a3d1b85da7
excelsior-coordinator is an agent published in the GitHub repository cveralyon/axel-setup (4 stars, last pushed 1mo ago), licensed MIT. It adds 35 tokens to every session and 561 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 agents, from other repositories
syllago-author
/home/hhewett/.local/src/syllago/content/agents/syllago-author/AGENT.md.
feature-flow
Build, test, verify, and review an already planned feature. Operates on a feature branch off trunk; prepares a PR but does not merge.
review
Review PR and build output for quality, security, and compliance. Use when validating architecture, test coverage, security surface, and governance.
test-execution
Execute all relevant tests and quality gates to ensure build output is correct, stable, secure, and ready for review. This is feature-flow's Phase 3 (and Phase 3.5 for live-system verification) — local, pre-push verification. Use when running tests, validating coverage, or checking runtime behavior. Distinct from the…
design
Convert the specification into a clear, actionable technical design with architecture, components, interfaces, and data flows. Use when translating requirements into a buildable system design.
learn
Product retrospective agent. Runs after a release, after a measure agent anomaly flag, or at end of sprint. Maps findings to DORA AI capabilities and produces plan agent action items. Distinct from fawkes learn.md which handles platform incident postmortems.