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 skills add gmickel/flow-next --skill flow-next-plan-reviewgit clone --depth 1 https://github.com/gmickel/flow-nextWrote 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/gmickel/flow-next/flow-next-plan-review)<a href="https://agentmods.dev/skills/gmickel/flow-next/flow-next-plan-review"><img src="https://agentmods.dev/badge/skills/gmickel/flow-next/flow-next-plan-review/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/gmickel/flow-next/flow-next-plan-review"><img src="https://agentmods.dev/badge/skills/gmickel/flow-next/flow-next-plan-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00032 | $0.01914 |
| Opus 5.5 | $0.00013 | $0.00766 |
| Sonnet 5.5 | $0.00006 | $0.00383 |
| Haiku 4.5 | $0.00003 | $0.00191 |
Grade A, and why
flow-next-plan-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 19d 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 — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan Review Mode
Workflow is backend-split. Read workflow.md for common orchestration and backend resolution, then read ONLY the file matching the selected review backend:
BACKEND=codex→ workflow-codex.mdBACKEND=copilot→ workflow-copilot.mdBACKEND=cursor→ workflow-cursor.mdBACKEND=claude→ workflow-claude.mdBACKEND=host→ workflow-host.md
Do not load the other backend files. BACKEND=none and an explicit
--review=rp or --review=export terminate from the common workflow without
loading any backend file.
Conduct a John Carmack-level review of spec plans.
Role: Code Review Coordinator (NOT the reviewer)
Backends: Codex CLI (codex), GitHub Copilot CLI (copilot), Cursor CLI (cursor),
Claude Code CLI (claude), or host-native (host)
Read working-rules.md first unless you already have this run; it holds for every step of this skill.
Preamble — execute common routing exactly once
Read and execute workflow.md Phase 0 once. It defines $FLOWCTL,
parses an explicit --review mode before configured-backend resolution,
resolves SPEC_ID, and handles ASK, none, rp and export. Never invoke
flowctl review-backend a second time.
Backend Selection
Priority (first match wins):
--review=codex|copilot|cursor|claude|host|none- Per-spec
default_review FLOW_REVIEW_BACKEND.flow/config.jsonreview.backend- Error — no auto-detection
Configured values accept backend[:model[:effort]]; cursor takes a model but
no effort, claude takes claude[:<model>[:<effort>]], and host and none are bare-only.
Common Critical Rules
- The coordinator never self-declares a verdict.
- Stick to one backend for the full review/fix cycle.
- If
REVIEW_RECEIPT_PATHis set, every review verdict writes a receipt. - Any backend/transport failure outputs
RETRY: no verdict (backend or transport failure)and stops; never silently fall back to a different backend. When itsCLI message:reports a usage, credit or spend limit, report that message and stop instead ofRETRY:; a retry fails the same way. Autonomous callers receive the same retry terminal and decide whether to re-enter. A no-verdict dispatch is refunded and recorded by flowctl; never manually reset the review counter for a transport failure. Exit 5 /TRANSPORT_UNHEALTHYmeans stop automatic retries and repair the backend. noneskips only when selected explicitly or resolved from configuration.- Foreground rule: run every
flowctl <backend> plan-reviewcall as one blocking foreground Bash call with a generous timeout (10 minutes; verdicts typically land in 1–7) — neverrun_in_background+ monitor/poll (a background completion does not reliably resume a subagent context). Host-backend subagent dispatches are also blocking.
What ships with it
9 files 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.
- 19d ago Changed · -14 lines dc644e22b2d5
- 21d ago Changed · -4 lines 8a3b71511441
- 23d ago Changed · +5 lines ee737262939f
- 28d ago Changed · +2 lines 850e0198c6cb
- 1mo ago Changed · +9 lines 8dccdc0bf617
- 1mo ago Changed · +1 lines f6c87e0ef586
- 1mo ago First seen · 156 lines · 32 tokens per session scan A d8ca92f063ff
flow-next-plan-review is a skill published in the GitHub repository gmickel/flow-next (711 stars, last pushed today), licensed MIT. It adds 32 tokens to every session and 1,914 once invoked, about $0.0001 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
pr
Comprehensive PR/issue review - analyzes architecture, tests, identifies unrelated changes mixed in, drafts review comment or issue comment. Use when user asks to review a PR, check a PR, look at PR changes, or comment on an issue.
st-lint
Smalltalk best-practices linter for Tonel files. Use when validating .st files before importing to the Smalltalk image (Pharo or Squeak), checking code quality after editing, or diagnosing style issues in a package.
gate-check
Final quality gate before reporting task completion (Gate 3). Fills confidence assessment, runs supplementary verification for <95% items, completes self-check checklist. Writes PASS/FAIL result to subtask.md, then calls autoworker:dispatch for routing.
polish
Polish a completed code change with a bounded independent review protocol. Use after implementation and before final approval or PR to review intent, acceptance criteria, non-goals, diff, relevant files, verification, and previously rejected findings.
verify-change
A change-checking skill that reviews code differences and checks whether related documentation, tests, and records were updated.
verify-quality
A code-quality checker that measures complexity, size, naming, and common code smells. It reports problems such as duplicated code, unused code, and overly long functions.