epic-review

A review workflow for a large change made up of several connected units. It examines the complete set of changes against the original acceptance criteria, which are the conditions the work must meet.

In plain words
What is it for?
Use it to review an entire feature or project change after all its units have landed.
Why use it?
Reviewing each part separately can miss broken connections, missing requirements, or design problems that only appear when everything is combined.

Command

Install

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.

agentmods
npx agentmods add commands/sjarmak/coding-agent-workflows/epic-review
Clone the repo
git clone --depth 1 https://github.com/sjarmak/coding-agent-workflows
Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 428 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 2d ago against content hash b8399e9056bb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

targets/claude/commands/epic-review.md · 52 lines

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.

Changes

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.

  1. 2d ago First seen · 52 lines · 24 tokens per session scan A b8399e9056bb

Subscribe to this mod's changes

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.