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 skills add stefan-jansen/coding-agent-toolkit --skill decomposegit clone --depth 1 https://github.com/stefan-jansen/coding-agent-toolkitWrote 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/stefan-jansen/coding-agent-toolkit/decompose)<a href="https://agentmods.dev/skills/stefan-jansen/coding-agent-toolkit/decompose"><img src="https://agentmods.dev/badge/skills/stefan-jansen/coding-agent-toolkit/decompose/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/stefan-jansen/coding-agent-toolkit/decompose"><img src="https://agentmods.dev/badge/skills/stefan-jansen/coding-agent-toolkit/decompose.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00060 | $0.01598 |
| Opus 5.5 | $0.00024 | $0.00639 |
| Sonnet 5.5 | $0.00012 | $0.00320 |
| Haiku 4.5 | $0.00006 | $0.00160 |
Grade A, and why
decompose 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 — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
decompose - turn the spec into issues
You are running the PLAN step of the workflow. Input is a spec.md written
by align. Output is plan.md in the same work unit, in the shape defined
below, which plan-issues parses to create a GitHub milestone and one issue per
planned issue.
This step must not ask the user anything. The spec is the contract; if it is
too incomplete to decompose, say so and send the user back to /align rather
than interrogating them here. That rule is what makes this step runnable
headlessly on either host.
Arguments
| Arg | Required | Default | Meaning |
|---|---|---|---|
<path> |
no | active work unit's spec.md |
The spec to decompose |
If no path is given, locate the active work unit: walk up from the working
directory to a .workspace/work/ (or work/) directory, then take the most
recently modified subdirectory containing a spec.md. If that is ambiguous,
name the candidates and pick the newest rather than asking.
Mechanism
Claude Code: enter plan mode (EnterPlanMode) and do the exploration and
decomposition there, then write plan.md on exit. Plan mode is how you think;
it is not the deliverable. A plan that stays in the transcript has not run this
step.
This step is named decompose, not plan, because /plan is Claude Code's
built-in prefix for entering plan mode and cannot be claimed by a skill or a
command. Typing /plan gets you plan mode and the model's own default
planning, which is the behaviour this step exists to replace.
Codex: run the decomposition directly, read-only, and write plan.md.
Both hosts produce the same file. Nothing downstream reads anything else, so no JSON schema and no structured-output mode is involved.
Required shape of plan.md
plan-issues parses this file. Any deviation makes the next step abort.
# Plan: <work unit name>
<one or two paragraphs: what this decomposes, and the gating order>
## <optional free-form sections: context, findings, architecture, verification>
### Milestone: `<version> - <title>`
**Issue 1 - <issue title>**
<body: files touched, the change, how it is verified, what "done" means>
**Issue 2 - <issue title>**
<body>
What ships with it
1 file 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.
- 2d ago Changed · +29 lines 253dc4d5641b
- 29d ago First seen · 114 lines · 60 tokens per session scan A e77e64482dc1
decompose is a skill published in the GitHub repository stefan-jansen/coding-agent-toolkit (33 stars, last pushed 2d ago), licensed MIT. It adds 60 tokens to every session and 1,598 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-17.
Other skills, from other repositories
story-readiness
Is a story implementation-ready? Checks clear acceptance criteria, open questions, ADR refs. READY/NEEDS WORK/BLOCKED/NOT ASSESSED.
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
projects
List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.
ring:mapping-feature-relationships
Mapping how features relate and phasing the work: categorizing PRD features, grouping them into domains, charting cross-feature journeys, dependencies, and integration points, and defining the binding Phases that plan.md mirrors one-to-one at Gate 7. Gate 2 of ring:planning-large-features; runs after…