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/bostonaholic/team/decomposing-intentnpx skills add bostonaholic/team --skill decomposing-intentgit clone --depth 1 https://github.com/bostonaholic/teamWrote 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/bostonaholic/team/decomposing-intent)<a href="https://agentmods.dev/skills/bostonaholic/team/decomposing-intent"><img src="https://agentmods.dev/badge/skills/bostonaholic/team/decomposing-intent.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 | $0.00029 | $0.00783 |
| Opus 5 | $0.00015 | $0.00392 |
| Sonnet 5 | $0.00006 | $0.00157 |
| Haiku 4.5 | $0.00003 | $0.00078 |
Grade A, and why
decomposing-intent 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 today.
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 — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Decomposing Intent
Capture user intent in 1-task.md, neutral codebase questions in 2-questions.md, conditional requirements in 3-prd.md, and resolved multi-repo scope in 4-repos.md.
Artifact invariants
topic is identical across artifacts: the kebab portion of <id> after removing <TICKET>- or <YYYY-MM-DD>-. The questioner chooses it once; downstream phases copy it verbatim. Never use the ticket, date, or a rewording. ticketId appears only in 1-task.md. Full schema: skills/artifact-frontmatter/SKILL.md.
Read references/artifact-templates.md before writing the artifacts. Keep 1-task.md under 80 lines. Write 8–15 questions answerable from code. Codebase context may name files, modules, and vocabulary, but MUST NOT state the goal or desired outcome; it replaces legacy brief.md.
Call the Skill tool with product-requirements-doc when a request is vague/underspecified, spans multiple user stories, is cross-cutting, or replaces existing behavior. Then write docs/plans/<id>/3-prd.md with phase: prd and reference it from 1-task.md. Skip it for simple, well-scoped requests.
Research isolation
Phrase questions about the codebase, never the goal. Bad: “How should we add rate limiting?” Good: “Where do incoming HTTP requests enter the application and what middleware chain do they pass through?” Each question must remain useful to a stranger who does not know the feature (principle-blind-the-investigator).
Multi-repo safety
Infer multiple repos only when the description names them or explicitly names cross-repo scope; otherwise use single-repo mode and record that assumption. Never invent or silently expand scope.
Resolve candidate repos autonomously. First require each <name> to match ^[A-Za-z0-9._-]+$ and not equal . or ..; path separators, absolute paths, traversal, $(), backticks, and other shell metacharacters fail. Pass names/paths as single argv arguments, never interpolate them into shell strings (principle-never-interpolate).
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- today Changed · -192 lines · -27 tokens per session 6813ecece7c0
- yesterday Changed · +4 lines 10bbab16cce4
- 5d ago First seen · 228 lines · 56 tokens per session scan A da52ae98e661
decomposing-intent is a skill published in the GitHub repository bostonaholic/team (11 stars, last pushed today), licensed MIT. It adds 29 tokens to every session and 783 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 2026-08-30.
Other skills, from other repositories
tutti-app-release
Set up, review, run, or debug external repositories that publish a Tutti workspace app through the reusable Tutti App Release GitHub Actions workflow. Use for caller workflows, tutti.app.json manifests, @tutti-os/app-release-tools, S3/CloudFront release hosting, latest.json, versions.json, catalog.json, catalog-only…
analyze-performance-traces
Analyze Chrome, Chromium, Electron, React DevTools, or Perfetto-compatible JSON traces and audit user-reported profiling findings without loading large artifacts into context; prove trigger-to-render/layout chains, separate measured facts from source inference, find exact code choke points, classify forced layout and…
tutti-test-audit
Audit, design, write, materially revise, or remove Tutti tests. Use whenever Codex changes or reviews unit, component, conformance, integration, regression, platform, or repository tests; enforce a protected product contract, credible failure, correct owning boundary, negative-control evidence, overlap review…
tutti-agent-workspace-app
Build or evolve a complex agent-enabled Tutti workspace app repository. Use for Tutti apps with web/server/shared monorepos, @tutti-os/agent-acp-kit local agent runtimes, kit-owned TUTTICLI agent/composer discovery, dynamic agent catalogs, run-scoped MCP tool gateways, app-owned package builders, web-first debugging…
assimilate-popular-workflows
This skill should be used when the user asks to "find skills in the wild", "assimilate popular workflows", "discover SKILL.md files in repos", "research external skills", "find workflow patterns", "survey the skill landscape", "what skills exist out there", or wants to investigate public repositories for extractable…
process-builder
Scaffold new babysitter process definitions following SDK patterns, proper structure, and best practices. Guides the 3-phase workflow from research to implementation.