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-draft-triagenpx skills add KlausFreiberufler/devflow-mcp --skill devflow-draft-triagegit 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-draft-triage)<a href="https://agentmods.dev/skills/klausfreiberufler/devflow-mcp/devflow-draft-triage"><img src="https://agentmods.dev/badge/skills/klausfreiberufler/devflow-mcp/devflow-draft-triage.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 | $0.00000 | $0.01385 |
| Opus 5 | $0.00000 | $0.00692 |
| Sonnet 5 | $0.00000 | $0.00277 |
| Haiku 4.5 | $0.00000 | $0.00138 |
Grade A, and why
devflow-draft-triage 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 4d 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: devflow-draft-triage
Pre-review-done cleanup. The
no-pending-draftsGate (DF-320) blocksreview → donewhenever any draft from this or earlier flows is stillpending. This skill walks them down systematically.
When to use
In the review state, before emitting the testing-tokens and the final flow_update({currentState: 'done'}). If knowledge_draft_list({status: 'pending'}) returns ≥ 1, this skill runs.
Why this exists
Background-harvested drafts accumulate. Without explicit triage:
- The Gate fires unexpectedly during
review → done, breaking the loop. - True wiki-worthy drafts get lost in the noise of plan-artefacts.
- Plan-artefacts pollute the candidate-pool that powers
extend > dismissdecisions later.
Process
1. Pull pending drafts
knowledge_draft_list({ status: 'pending' })
If the result is empty: emit the skill-token immediately with evidence: { reviewed: 0 } and exit.
2. Classify each draft
For every draft, decide a category based on title + sourceFlowIds + body:
| Category | Action | Reason |
|---|---|---|
| Real Wiki-worthy (runbook from a hotfix, pattern from a reusable mechanism, lesson from a substantive audit) | knowledge_draft_accept |
Iron Law extend > dismiss: this content compounds the wiki. |
| Extend-candidate (a related wiki entry already exists and should grow) | knowledge_draft_reject({ notes: "extend → <slug>" }) THEN knowledge_check_resolve({ resolutionType: 'extend', entityType, entityId, body, rationale }) |
Don't create a parallel page — fold into the existing entry. |
Plan-artefact (auto-harvested from an implementation-plan.md attachment — title looks like "Pattern candidate: DF-XYZ Implementation Plan" or "# Goal") |
knowledge_draft_reject({ notes: "plan-artefact (DF-406 Iron Law)" }) |
Pläne leben am Flow-Attachment, nicht im Wiki. |
| True Duplicate (two drafts cover the exact same scope, one ADR + one Runbook) | accept the better form, reject the weaker with notes: "dedup → <id>" |
Wiki kompakt halten. |
| Honest false positive (heuristic over-classified) | knowledge_draft_reject({ notes: <substantive reason ≥ 10 chars> }) |
Acceptable — but rare. Audit log keeps the reason. |
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.
- 4d ago First seen · 101 lines · 0 tokens per session scan A e3013efce507
devflow-draft-triage is a skill published in the GitHub repository KlausFreiberufler/devflow-mcp (1 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,385 tokens. 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.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…