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 skills/klausfreiberufler/devflow-mcp/devflow-reviewingnpx skills add KlausFreiberufler/devflow-mcp --skill devflow-reviewinggit clone --depth 1 https://github.com/KlausFreiberufler/devflow-mcpWrote 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/klausfreiberufler/devflow-mcp/devflow-reviewing)<a href="https://agentmods.dev/skills/klausfreiberufler/devflow-mcp/devflow-reviewing"><img src="https://agentmods.dev/badge/skills/klausfreiberufler/devflow-mcp/devflow-reviewing.svg" alt="Measured on agentmods" 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 | $0.00034 | $0.00741 |
| Opus 5 | $0.00017 | $0.00370 |
| Sonnet 5 | $0.00007 | $0.00148 |
| Haiku 4.5 | $0.00003 | $0.00074 |
Grade A, and why
devflow-reviewing 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 5d 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DevFlow — Review State
The flow is review. The agent has submitted work; you are checking it and preparing handover notes for the user.
Iron Law — Review stays in the flow
- No external delegation. Run the diff analysis inline. Don't farm out to other tool-skill systems; the review must be auditable as part of the flow's agent-trace.
- Verify, don't trust. Every acceptance criterion gets a real verification command (
devflow-verification-gateskill governs this) — no "should work" claims. - Document for the user. Write
agentSummary+testingInstructionsso the user can re-verify in 2 minutes without re-reading the diff.
Self-Review Steps
How you read the diff depends on gitEnabled (see devflow-core Git Mode):
gitEnabled: true:
- Run
git diff <base-branch>...HEADto see everything this flow added - For each changed file: plan-fit / bugs / debug-leftovers / coverage / convention check
- Fix findings with additional commits on the same branch
gitEnabled: false:
- Run
git status(read-only) to see modified files, or list them from your edit history - Open each modified file and review against the same checks
- Fix findings inline — no commits needed
In either mode:
- Check acceptance criteria from the flow — each one ticked off?
Before Marking Done
review → done behaviour depends on Self-Approval mode (DF-302, see devflow-core):
allowSelfApproval: false (default — most projects):
You cannot transition. Your job stops at:
- ✅ Clean self-review complete
- ✅
agentSummarypopulated viaflow_update - ✅
testingInstructionspopulated viaflow_update - ✅ If
gitEnabled: true— commits attached to the flow, PR merged - ✅ Docs updated if applicable
Then show the user the gate.userMessage when you hit the 403, and stop. The user tests in DevFlow UI and clicks approve.
allowSelfApproval: true:
You may self-transition by emitting discipline-tokens for every skill in gate.requiredSkills:
- Run
devflow_token_emit({ flowId, skillName: '<each-required-skill>', evidence: {...} })for each - Then
flow_update({ flowId, currentState: 'done', selfApproved: true, disciplineTokens: [<token1>, <token2>, ...] }) - The audit-trail will record
code_approved_by: 'agent:devflow (selfApproved with N tokens)'
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.
- 5d ago First seen · 58 lines · 34 tokens per session scan A ec76a3a358a5
devflow-reviewing is a skill published in the GitHub repository KlausFreiberufler/devflow-mcp (1 stars, last pushed 2d ago), licensed MIT. It adds 34 tokens to every session and 741 once invoked, about $0.0002 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…