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 KlausFreiberufler/devflow-mcp --skill devflow-receiving-reviewgit 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-receiving-review)<a href="https://agentmods.dev/skills/klausfreiberufler/devflow-mcp/devflow-receiving-review"><img src="https://agentmods.dev/badge/skills/klausfreiberufler/devflow-mcp/devflow-receiving-review.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 | $0.00061 | $0.01229 |
| Opus 5 | $0.00030 | $0.00615 |
| Sonnet 5 | $0.00012 | $0.00246 |
| Haiku 4.5 | $0.00006 | $0.00123 |
Grade A, and why
devflow-receiving-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 7d 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: devflow-receiving-review
Iron-Law port of Superpowers
receiving-code-review. Code-review without a structured triage is just opinion; this skill turns reviewer-output into a checklist with deliberate decisions and an audit trail.
When to use
In review state, after a code-review has been performed (manually by a human, or via a subagent like the project's code-reviewer agent). The skill triages the raw review-output into actionable rows.
Severity schema
Every finding gets exactly one severity:
| Severity | Definition | Effect on done |
|---|---|---|
| Critical | Bug, security issue, data-loss risk, or behaviour that contradicts an accepted ADR. | Blocks done — must be fixed (or explicitly overridden as break-by-design via Hook 6 ADR-Compliance). |
| Important | Likely-bug, design smell, ambiguous spec, missing test for a non-trivial path. | Should be addressed; rejection requires a written reason. |
| Minor | Cosmetic, style, naming, code-smell that doesn't affect behavior. | Optional; rejection is acceptable without long justification. |
Borderline cases: when in doubt, assign the higher severity. It's cheaper to triage-down than to discover a missed Critical at production.
Process
1 · Collect findings
Gather every finding from the review-source (subagent stdout, PR-comments, oral feedback). Number them. Don't filter at this stage.
2 · Triage per finding
For each finding, capture:
- id: F1
severity: Critical | Important | Minor
location: <file>:<line> | <component> | <general>
observation: <reviewer's claim, verbatim or summarized>
verification: <what you actually checked — read the code, ran the test, etc.>
decision: fix | reject | knowledge-draft
reasoning: <why fix or why reject; what knowledge to capture if draft>
Iron Law: verification is non-optional. A finding's verification field can never be "trusted reviewer". Read the cited code yourself, run the relevant test, or check the actual ADR/spec. If you cannot verify within ~5 min, default the decision to fix — the reviewer's caution outweighs your interpretation.
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.
- 7d ago First seen · 111 lines · 61 tokens per session scan A 850d7463a9c0
devflow-receiving-review is a skill published in the GitHub repository KlausFreiberufler/devflow-mcp (1 stars, last pushed 4d ago), licensed MIT. It adds 61 tokens to every session and 1,229 once invoked, about $0.0003 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
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…