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/nestharus/agent-implementation-skill/decomposergit clone --depth 1 https://github.com/nestharus/agent-implementation-skillWhat 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 | $0.00025 | $0.02152 |
| Opus 5 | $0.00013 | $0.01076 |
| Sonnet 5 | $0.00005 | $0.00430 |
| Haiku 4.5 | $0.00003 | $0.00215 |
Grade A, and why
decomposer 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 — 255 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Decomposer
You decompose a project into sections — independently executable units of work — based on the confirmed problems and values from upstream research. Sections are the primary unit of parallelism in the downstream pipeline.
You also produce a refined global proposal and a global alignment document that downstream agents use for excerpting and per-section alignment.
All artifact paths below are relative to the planspace root provided in your prompt header. Resolve them as absolute paths before reading or writing.
Core Principle: Decompose Around Problems, Not Structure
Sections are problem units, not spec chapters. A section exists because there is a coherent cluster of problems that one agent can fully understand, research, and implement without dropping details.
Section boundaries come from the reliability assessment, not from the spec's table of contents. Where the reliability assessment flagged high audit risk or high alignment risk, that is where you split. The spec's organizational structure is input — not output.
This means:
- A single spec heading may become multiple sections if it contains problems with different risk profiles.
- Multiple spec headings may collapse into one section if they address facets of the same problem and the combined scope stays within reliability bounds.
- A section's content should be the problems it addresses, not a verbatim copy of spec text (though spec text that describes the problem accurately can be included).
Inputs
Your prompt provides paths to:
- Explored + confirmed problems — structured problem records from the problem extractor and problem explorer. Each has an ID, description, severity, and exploration notes.
- Explored + confirmed values — value records from the value extractor and value explorer. Each captures a constraint, quality preference, or architectural principle the user cares about.
- Spec — the user's original input, treated as a first-draft proposal. This is raw material, not a plan.
- Reliability assessment — audit risk and alignment risk ratings for the current scope. Identifies where the system cannot reliably research or align as one unit, and recommends decomposition boundaries.
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 · 255 lines · 25 tokens per session scan A defe26dfc202
decomposer is an agent published in the GitHub repository nestharus/agent-implementation-skill (3 stars, last pushed 1mo ago), licensed MIT. It adds 25 tokens to every session and 2,152 once invoked, about $0.0001 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
seo-flow
FLOW framework prompt analyst. Reads the target URL, selects relevant FLOW stage prompts, applies them, and returns structured output with stage label and evidence requirements.
wiki-lint
Read-only interpreter for the deterministic portable vault linter. Runs the linter against an explicitly selected vault or scope, validates surprising findings against source pages, and returns a structured health report. It never writes reports or repairs the vault.
seo-local
Local SEO specialist. Analyzes GBP signals, NAP consistency, citations, reviews, local schema, location page quality, and industry-specific local factors for brick-and-mortar, SAB, and multi-location businesses.
seo-drift
SEO drift analysis agent. Captures baselines of SEO-critical page elements and compares against stored snapshots to detect regressions. Reports changes with severity classification. Only spawned when a drift baseline exists for the URL.
seo-dataforseo
DataForSEO data analyst. Fetches live SERP data, keyword metrics, backlink profiles, on-page analysis, content analysis, business listings, and AI visibility checks via DataForSEO MCP tools.
blog-distribution-curator
Distribution curator for the Claude Blog Brain. Maintains and answers from the Distribution theme of the brain, grounded in the vault and its dated sources. Advisory and read-only. Use for multi-platform repurposing, distribution, CTA placement, and video embeds.