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/epic-reviewgit 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 | $0.00024 | $0.00428 |
| Opus 5 | $0.00012 | $0.00214 |
| Sonnet 5 | $0.00005 | $0.00086 |
| Haiku 4.5 | $0.00002 | $0.00043 |
Grade A, and why
epic-review 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.
What it actually says
Workflow: Epic Review
Individual units pass their own implement-review gate, but the assembled
whole can still be wrong: interfaces that don't line up, a criterion that fell
between two units, an architectural drift only visible across the set. This
workflow reviews at the epic boundary.
Inputs
| Input | Source | Description |
|---|---|---|
epic |
caller | The epic whose constituent units have all landed. |
base_ref |
caller | Ref before the first unit landed (the full-epic diff base). |
Steps
1. assemble
Collect the full diff across all units (git diff {base_ref}...HEAD) and the
epic's original acceptance criteria. This is a different artifact than any one
unit's diff.
Exit: the whole-epic diff and the original criteria, side by side.
2. cross-cutting review (needs: assemble)
Run code-review over the combined diff, and where a multi-model runtime is
available add review (multi-angle) for independent perspectives. code-review
is the portable gate that always runs. Look specifically for problems that only
appear at the seams:
- interfaces between units that don't actually fit
- an epic-level acceptance criterion no single unit owned
- duplicated logic that emerged because units were built in isolation
- architectural drift from the intended target
For changes touching auth, input handling, secrets, or endpoints, also run
security-review over the combined surface.
Exit: findings classified blocking vs non-blocking.
3. decide (needs: cross-cutting review)
If blocking findings exist, route fixes back as new units through
implement-review (don't patch inline at the epic level). If clean, record the
epic-level verification and close.
Exit: epic accepted, or fix-units dispatched.
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 · 52 lines · 24 tokens per session scan A b8399e9056bb
epic-review is a command published in the GitHub repository sjarmak/coding-agent-workflows (2 stars, last pushed 1mo ago), licensed MIT. It adds 24 tokens to every session and 428 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.
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.
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.
help
Show all DeepInit commands + key options, grouped and ordered by how often you'll use them. Instant, no analysis.