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 commands/sjarmak/coding-agent-workflows/decomposegit clone --depth 1 https://github.com/sjarmak/coding-agent-workflowsWhat 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 | $0.00019 | $0.00403 |
| Opus 5 | $0.00010 | $0.00201 |
| Sonnet 5 | $0.00004 | $0.00081 |
| Haiku 4.5 | $0.00002 | $0.00040 |
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 yesterday.
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.
What it actually says
Workflow: Decompose
For work too large for one implement-review pass. Produces a dependency-ordered set of units, each small enough to implement and review on its own.
Inputs
| Input | Source | Description |
|---|---|---|
epic |
caller | The large body of work to break down. |
context |
caller | Acceptance criteria, constraints, target architecture. |
Steps
1. map
Read the epic and its acceptance criteria. Identify the natural seams, the points where work can be split so each piece is independently testable and reviewable. Split on reasons to change and on what can ship alone, not on line count.
Exit: a list of candidate units with one-line scopes.
2. order (needs: map)
Establish dependencies between units (which must land before which). Flag units that can run in parallel. Each unit should have its own acceptance criteria derived from the epic's.
Exit: a dependency-ordered (DAG) breakdown; parallelizable units marked.
3. review-decomposition (needs: order)
Review the breakdown itself as a gate: does the union of the units actually
cover the epic's acceptance criteria? Are any units still too large to
implement-review in one pass? Is any "unit" actually two reasons-to-change
glued together? Reject and re-split if so. Where a multi-model runtime is
available, dispatch review for an independent check; otherwise apply the
coverage-and-sizing gate directly.
Exit: a breakdown whose units each fit one implement-review pass and whose
union covers the epic.
Hand-off
Each resulting unit is then driven through the implement-review workflow,
independently, in dependency order.
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.
- yesterday First seen · 51 lines · 19 tokens per session scan A ad20d454ccf6
decompose is a command published in the GitHub repository sjarmak/coding-agent-workflows (2 stars, last pushed 1mo ago), licensed MIT. It adds 19 tokens to every session and 403 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 commands, from other repositories
plugin-update
Upgrade DeepInit to the latest version — pulls the newest from the marketplace (on one confirm), then guides the host-correct reload. Ends the "is my plugin stale?" dance.
check
Is the context layer still true? 0-token staleness + broken-citation audit (no LLM, CI-friendly). Add --status for the fast hash-only subset.
customize
Tune a DeepInit run with buttons — depth, issue detection, outputs, scope, cost, and the freshness/notification settings (disable the nudge, change its cadence/time-window) — no flags to type. Opens a native multiple-choice picker, then runs.
version
Which DeepInit version is actually running right now? Prints the LOADED version, checks it against the on-disk version, and tells you if you need to reload. No analysis.
doctor
DeepInit preflight — tools, scope, resolved config (and whether it's valid), enabled issue families, estimated cost. 0 tokens, no LLM. Offers to install the freshness hooks.
help
Show all DeepInit commands + key options, grouped and ordered by how often you'll use them. Instant, no analysis.