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/brainstorm-loopgit 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 | $0.00021 | $0.00329 |
| Opus 5 | $0.00010 | $0.00164 |
| Sonnet 5 | $0.00004 | $0.00066 |
| Haiku 4.5 | $0.00002 | $0.00033 |
Grade A, and why
brainstorm-loop 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: Brainstorm Loop
For feature design and "how should we approach X" questions. Forces divergent volume under a uniqueness constraint, then filters by failure analysis.
Inputs
| Input | Source | Description |
|---|---|---|
problem |
caller | The problem statement. Use the task title if dispatched. |
context |
caller | Constraints and prior art that define exclusion zones. |
Steps
1. brainstorm
Run brainstorm: produce many candidate approaches under one hard constraint.
No idea may take the same shape as any prior art or any earlier idea in this
session. Volume plus shape-uniqueness is what gets past the obvious answer.
Exit: a set of shape-distinct candidates.
2. premortem (needs: brainstorm)
Run premortem on the top candidates: for each, assume it failed and list why.
Drop candidates whose failure modes are fatal or unmitigable.
Exit: a shortlist of candidates that survive failure analysis.
3. converge (needs: premortem)
Run converge on the shortlist: pick one direction, state the trade-offs it
accepts, and record the runners-up so the decision is auditable later. Where
subagents are available, run it as a multi-agent debate; otherwise weigh the
shortlist directly in one pass.
Exit: one chosen direction + rejected alternatives with reasons.
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 · 42 lines · 21 tokens per session scan A 53ca223ac25c
brainstorm-loop is a command published in the GitHub repository sjarmak/coding-agent-workflows (2 stars, last pushed 1mo ago), licensed MIT. It adds 21 tokens to every session and 329 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.