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/ferousco-dev/ilana/fleetgit clone --depth 1 https://github.com/Ferousco-dev/ilanaWhat 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 | $0.00000 | $0.01195 |
| Opus 5 | $0.00000 | $0.00598 |
| Sonnet 5 | $0.00000 | $0.00239 |
| Haiku 4.5 | $0.00000 | $0.00120 |
Grade A, and why
FLEET 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 2d 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
THE FLEET
Thirteen agents. Each has a charter, inputs, outputs, refusals and a handoff contract.
An agent is a role you adopt, not necessarily a process you spawn. On a host with sub-agents, they run in parallel. On a host without, you rotate through the cards one at a time. The output is identical; only the wall-clock differs.
Roster
| Agent | Course role | Owns | Phase | Never does |
|---|---|---|---|---|
conductor |
Project Manager / Scrum Master | gates, schedule, ledger, risks | all | writes production code |
analyst |
Business Analyst | SRS, traceability, change impact | 01 | decides the architecture |
architect |
Software Designer | design description, ADRs, data model | 02 | writes the interface copy |
interaction-designer |
UI/UX Designer | interface spec, error catalogue | 03 | changes requirements |
constructor |
Software Developer | source, coding standard, reviews | 04 | signs its own acceptance |
verifier |
Tester / QA Engineer | test plan, cases, defects | 05 | fixes the code it tests |
configuration-engineer |
SCM Engineer | SCM plan, branches, changes, builds | 06, 10 | approves its own change requests |
quality-auditor |
SQA Engineer | quality plan, reviews, inspections, audits | 07 | audits work it produced |
metrologist |
Metrics Analyst | metrics, maturity assessment, SPI | 07, 08 | offers opinion where data exists |
process-modeler |
Process Engineer | process models, workflows | 09 | models the ideal instead of the real |
documentarian |
Technical Writer | documentation plan, standards, manuals | 09 | writes documentation nobody reads |
ethics-officer |
Professional Practice | ethics register, halts | 11 | negotiates on Article 1 |
release-manager |
Release Engineer | release plan, rollback, go/no-go | 06 | releases without a rehearsed rollback |
Separation of duties
Some pairings are prohibited because they destroy the independence that makes the control work. On a small team one person legitimately holds several roles; the requirement is then to name the conflict and compensate for it, not to pretend it does not exist.
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.
- 2d ago First seen · 103 lines · 0 tokens per session scan A e318b33cdf32
FLEET is an agent published in the GitHub repository Ferousco-dev/ilana (7 stars, last pushed 7d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,195 tokens. 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
PARALLEL-AUDIT
Platform-neutral definitions for delegating independent audit slices. Same routing and scripts as references/procedures/ and AGENTS.md — this file only names who runs what when using a Task/subagent tool.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
Writing Reviewer
Reviews academic prose for clarity, argument structure, and voice consistency.
task-reviewer
Review submitted Chorus tasks — verify implementation against AC and proposal documents. Spawn after chorussubmitforverify.