Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add restarter/lets-workflow/plugin install letsWrote 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/restarter/lets-workflow/review-workflow)<a href="https://agentmods.dev/skills/restarter/lets-workflow/review-workflow"><img src="https://agentmods.dev/badge/skills/restarter/lets-workflow/review-workflow/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/restarter/lets-workflow/review-workflow"><img src="https://agentmods.dev/badge/skills/restarter/lets-workflow/review-workflow.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 | $0.00056 | $0.01669 |
| Opus 5.5 | $0.00022 | $0.00668 |
| Sonnet 5.5 | $0.00011 | $0.00334 |
| Haiku 4.5 | $0.00006 | $0.00167 |
Grade A, and why
review-workflow scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 23d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
review-workflow (Dynamic Workflow asset)
This folder is the reference example of the Dynamic Workflow asset standard (see CLAUDE.md -> "Dynamic Workflow assets"). It is NOT a conversational skill: review.workflow.js is executed by the Workflow tool, invoked from /lets:review's Workflow Mode via:
Workflow({ scriptPath: "${CLAUDE_PLUGIN_ROOT}/skills/review-workflow/review.workflow.js", args })
${CLAUDE_PLUGIN_ROOT} is substituted at command-load time, so review.md carries the literal absolute path. Treat review.workflow.js as a template the command points at, not a script to reproduce inline.
What it does (off-context)
A multi-stage chain so per-agent reports never enter the conversation - only the final aggregate returns:
- Review - fan out the selected
lets:<name>review agents in parallel (structuredFINDING_SCHEMAoutput). - Reduce - split systemic (any tier) into its own section, NIT-filter the rest (unless small diff), dedupe (keep highest tier), sort by tier.
- Verify - for each BLOCKER/SUGGESTION, fan out
lets:skepticagents (2, or 3 for BLOCKER) to refute it. Apply the asymmetric drop rule: SUGGESTION drops on a simple majorityreal=false; BLOCKER drops only on near-unanimous high-confidence refute, otherwise downgrades. Countrefuted. - Aggregate - verdict over the verified set, per-agent summary, counts.
args contract (built by the command, passed as a JSON value)
| key | type | meaning |
|---|---|---|
agents |
[{name}] |
selected review agents (short names, no lets: prefix; exclude actor) |
mode |
string | PR-{n} | local-review | branch-review | file |
projectRoot |
string | absolute project root (agents must not read outside it) |
claudeMd |
string | CLAUDE.md context |
changedFiles |
string | changed-file list with stats (or single path for --file) |
code |
string | the diff (or full file content for --file) |
smallDiff |
bool | true keeps NIT findings (diff < 50 lines) |
systemicCheck |
bool | false for --file (no diff baseline) |
spec |
string | task description from the tracker's show (or the PR body); empty when unavailable - never a sentinel. Drives specBlock in the review prompt, and specBlockSkeptic in the verify prompt - the latter ONLY outside PR mode, since a PR-mode spec is the PR author's own task or plan file and a skeptic's real=false is a deterministic drop. No flag: PR mode is derived from mode, so it cannot be forgotten. Normalized in the script (non-string/whitespace-only → empty, 150 lines / 8000 chars, BEGIN/END SPEC delimiters inside the value neutralized on both sides - across every Unicode dash and with format characters stripped first - so it cannot escape its own fence) |
specSource |
string | where spec came from, per the command's Step 2.5 question: task | file | none | unresolved. Only none vs unresolved changes rendering, and the difference matters: none is the user saying no spec exists, so NO spec block is emitted at all; unresolved is a failed lookup, which still gets the "none reached this review" block because something may exist that we failed to read |
prBody |
string | the PR's own description, empty outside PR mode. Sanitized by the same fenced() as spec, 150 lines / 8000 chars |
prDiscussion |
string | the PR's gathered discussion - issue comments + non-empty review bodies + inline threads - empty outside PR mode. Same fenced(), 400 lines / 20000 chars: a discussion is legitimately longer than a spec. Kept SEPARATE from prBody so the script can label each half; merging them would make "what the author says" unattributable |
Both drive prContextBlock in the review prompt and nothing else. There is no skeptic counterpart by design: every word is written by the author of the code under judgement or by people commenting on it, and a skeptic's real=false is a deterministic drop. Like the spec in PR mode, there is no trusted case to carve out and therefore no flag to forget |
||
prTree |
bool | does the working tree hold the reviewed code? true for all non-PR modes and for PR mode after a checkout; false adds a REVIEW TREE warning to both prompts. Omitted on a PR-* mode is treated as false - failing toward "the tree may be wrong" rather than silently trusting it |
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.
- 23d ago Changed a10dfc7b71b5
- 1mo ago First seen · 62 lines · 56 tokens per session scan A 75b2fa4a2a1e
review-workflow is a skill published in the GitHub repository restarter/lets-workflow (17 stars, last pushed today), licensed MIT. It adds 56 tokens to every session and 1,669 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 2026-08-30.
Other skills, from other repositories
dekko-verify
Sanity-check a suspiciously low or zero call-graph result from dekko (getcallers, getcallees, findusages, impactedtests, unused) before concluding "no callers" or "dead code," or a heritage/throws-provenance result (query supertypes, query subtypes, query throws) that labels something (external) when you expect it to…
dekko-review-context
Give a code-review or PR-description flow a structural head start before reading a diff line by line. Trigger when the user asks for a PR description, a pre-merge summary, or invokes a code-review flow (/code-review, /review, or an equivalent) against a diff in a repo with a .dekko/ directory.
triage-report
Drain the .review/ report queue. Resolves un-triaged scan/audit reports (producer-agnostic — check-docs-consistency and any other scanner), dispatches the triage-report subagent (Sonnet) one report at a time for per-finding dispositions (promote / patch / dup / needs-investigation / dismiss), then the gateway absorbs…
fix
Read this repo's open issues, triage them, and open one pull request per issue that can be fixed without a judgement call. Issues that need a decision, or that look stale or superseded, are reported with a recommendation rather than guessed at.
watch-pr
Watch a GitHub pull request for CI status, reviews, comments, merge conflicts, and terminal states using the gh-watch extension. Use when the user wants to monitor a PR, wait for CI, or track PR progress.
review-health
Audit any repository's structural health and prompt surface, and file the findings as proposed epics and one-PR issues.