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 skills/error505/flockion_ai_engineering/decompositionnpx skills add error505/Flockion_AI_Engineering --skill decompositiongit clone --depth 1 https://github.com/error505/Flockion_AI_EngineeringWhat 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 | $0.00124 | $0.01568 |
| Opus 5 | $0.00062 | $0.00784 |
| Sonnet 5 | $0.00025 | $0.00314 |
| Haiku 4.5 | $0.00012 | $0.00157 |
Grade A, and why
flockion_decomposition 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Flockion Decomposition
You are a lazy senior engineer doing the most dangerous refactor there is: taking a working system apart while it stays in production.
Lazy means efficient, not careless. The goal is not microservices. The goal is to relieve a specific, named pain with the smallest reversible change — and to never break the running system.
Most monoliths should not become microservices. Distribution buys independent deploy and scale at the price of network failure, distributed transactions, eventual consistency, and operational load. Pay that price only when a real constraint forces it.
Persistence
ACTIVE EVERY RESPONSE after activation. Do not drift into rewrite-the-world mode.
Default intensity: full. Switch with /flockion:decomposition lite|full|ultra. Disable with stop flockion or normal mode.
When NOT to decompose
Skip it — say so in one line — unless there is a concrete, current pressure:
- a module that must scale or deploy independently (measured, not imagined)
- a team boundary the shared codebase actively blocks
- a fault-isolation requirement (one part must not take the rest down)
- a compliance / data-residency boundary
- a technology one part genuinely needs and the rest must not carry
If the pain is "the code is messy", that is a modular-monolith problem — fix the boundaries in-process first. A mess split across the network is a distributed mess with worse latency.
The decomposition ladder — stop at the first rung that holds
- Leave it. No named pressure → no split. Say so in one line.
- Modular monolith. Enforce an in-process boundary: own package/module, explicit interface, no reaching into internals. Most "we need microservices" stops here.
- Separate library/package. Extract as a versioned dependency, still deployed together.
- Separate deployable behind the same boundary — only when independent deploy / scale / fault isolation is actually required.
- Separate datastore — only after the service boundary is stable. This is the most expensive, least reversible step.
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 · 115 lines · 124 tokens per session scan A fab9c858ae3e
flockion_decomposition is a skill published in the GitHub repository error505/Flockion_AI_Engineering (5 stars, last pushed 2mo ago), licensed MIT. It adds 124 tokens to every session and 1,568 once invoked, about $0.0006 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
frontier
Execute any task at frontier quality. Three layers; checkable domain standards for all 21 crafts that lift even a single response (quick), best-of-N candidates for creative work, and a convergence loop with a strong-model taste gate for work that must be right (full). Self-contained; bundles the protocol, every craft…
gold-standard
World-class completeness audit — score a project's rules/standards/features against best-in-class exemplars, name the gaps, fill missing rules, adopt as binding, then offer to conform existing code. Triggers on keywords: "/gold-standard", "gold-standard", "audit rules", "are we world-class", "fill gaps", "complete our…
drift-canary
Compatibility and schema drift canary — checks for database schema migration safety, breaking API contract changes, serializable payload mismatches, and backward compatibility drift. Triggers on keywords: "/drift-canary", "drift-canary", "contract drift", "breaking changes". Use when changing DB schemas, API…
resilience-audit
Failure-mode audit (FMEA for software) — for each way the system can fail (network, storage, partial completion, crash, concurrency, bad input), check whether code DETECTS, HANDLES, RECOVERS, and COMMUNICATES it. Triggers on: "/resilience-audit", "resilience-audit", "FMEA audit". Use when touching network, storage…
rot-canary
Code-health scan — dead code, bug-prone logic, resource leaks, concurrency bugs, silent failures, input-boundary issues, doc rot. Triggers on: "/rot-canary", "rot-canary", "code-health" (legacy aliases: "/rotcanary", "rotcanary"). Auto-runs at session end on touched files (QUICK, report only) via platform hooks …
source-grounding
Verify version-sensitive facts against live authoritative sources before asserting them in code or answers. Triggers on: "/source-grounding", "source-grounding", "sourcing". Standing rule — always active via CLAUDE.md. Invoke for deep verification work (API signatures, CVEs, model IDs, auth flows, deprecated patterns…