Borrowing it
Nothing to install: this file belongs to lewing/helix.mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/lewing/helix.mcp/main/.copilot/skills/knowledge-refresh-triage/SKILL.mdgit clone --depth 1 https://github.com/lewing/helix.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/lewing/helix.mcp/knowledge-refresh-triage)<a href="https://agentmods.dev/skills/lewing/helix.mcp/knowledge-refresh-triage"><img src="https://agentmods.dev/badge/skills/lewing/helix.mcp/knowledge-refresh-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 5.1 | $0.00028 | $0.00410 |
| Opus 5 | $0.00014 | $0.00205 |
| Sonnet 5 | $0.00006 | $0.00082 |
| Haiku 4.5 | $0.00003 | $0.00041 |
Grade A, and why
knowledge-refresh-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 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.
What it actually says
Context
Use this when a plan, backlog, or knowledgebase contains earlier findings that may now be stale because code, tests, or documentation changed. The goal is to avoid carrying resolved issues forward as if they were still open.
Patterns
- Read the updated implementation, tests, and docs together before changing the knowledge artifact.
- Classify refreshed knowledge into three buckets:
- Fixed findings — issues that are now demonstrably resolved
- Still-open follow-up opportunities — real remaining work or product questions
- Durable knowledge worth retaining — conventions, positioning, or architecture facts likely to stay true
- Anchor each conclusion to specific files so future readers can re-verify it quickly.
- Prefer updating the active knowledge artifact already in use for the workstream (session plan, backlog doc, etc.) instead of scattering refresh notes across new files.
- If an earlier finding is fixed, explicitly say it should be treated as resolved, not backlog.
Examples
- A README review item becomes fixed after docs are rewritten and the knowledgebase is updated to move that item from backlog to resolved findings.
- A security hardening note is kept as durable knowledge only after code and regression tests both confirm the new behavior.
- A planning document retains a note that old inventory tables are stale while moving the current truth to a refreshed section at the top.
Anti-Patterns
- Updating a backlog from code alone without checking whether tests and docs also reflect the change
- Mixing resolved findings and future work in one undifferentiated bullet list
- Creating a brand-new notes file when an active plan or knowledge artifact already exists
- Treating stale historical analysis as current truth without a refresh pass
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 · 36 lines · 28 tokens per session scan A 4c2d7cf68aca
knowledge-refresh-triage is a skill published in the GitHub repository lewing/helix.mcp (4 stars, last pushed yesterday), licensed MIT. It adds 28 tokens to every session and 410 once invoked, about $0.0001 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
mnemon
Persistent memory CLI for LLM agents. Store facts, recall past knowledge, link related memories, manage lifecycle.
durable-session-state
Persist plans, scope decisions, evidence, and reviewer/critic verdicts to durable files during long or multi-phase tasks so work survives context compaction, session resumes, and handoffs. Use for swarm-mode tasks, before context grows large, when recording approval gates, and when resuming after compaction or a…
codspeed-optimize
Autonomously optimize code for performance using CodSpeed benchmarks, flamegraph analysis, and iterative improvement. Use this skill whenever the user wants to make code faster, reduce CPU usage, optimize memory, improve throughput, find performance bottlenecks, or asks to 'optimize', 'speed up', 'make faster'…
memory
Persistent, token-efficient project memory. When ON, maintains a .shob/memory/ folder of structured .md files so the full context of the project is NEVER lost across responses, sessions, or context compaction. Uses progressive disclosure — routes through a lightweight INDEX and loads only the files a task needs…
sivtr-memory
Retrieve shared local work memory: terminal activity, AI conversation history, prior decisions, validation evidence, debugging trails, recaps, and handoff context. Use before asking the user to repeat local work context.
brain-ingest
The process for digesting a conversation, document, or research result, classifying it, and writing it down as brain content (a root-page update or a new/updated page) through the brain CLI.