Borrowing it
Nothing to install: this file belongs to monarch-initiative/dismech. 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/monarch-initiative/dismech/main/.claude/skills/ker-evidence-triage/SKILL.mdgit clone --depth 1 https://github.com/monarch-initiative/dismechWrote 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/monarch-initiative/dismech/ker-evidence-triage)<a href="https://agentmods.dev/skills/monarch-initiative/dismech/ker-evidence-triage"><img src="https://agentmods.dev/badge/skills/monarch-initiative/dismech/ker-evidence-triage/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/monarch-initiative/dismech/ker-evidence-triage"><img src="https://agentmods.dev/badge/skills/monarch-initiative/dismech/ker-evidence-triage.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 | $0.00115 | $0.01438 |
| Opus 5 | $0.00057 | $0.00719 |
| Sonnet 5 | $0.00023 | $0.00288 |
| Haiku 4.5 | $0.00012 | $0.00144 |
Grade A, and why
ker-evidence-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.
How it starts
The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
KER evidence triage
A KER can be completely uncited. At the time this skill was written (09-03-2026), the AOP-Wiki XML export — the 08-06-2026 snapshot — held 2,369 KERs, of which 738 (31%) carry references and the other 1,631 (69%) carry none. A KER with an empty evidence block still renders as a clean arrow between two named events, and nothing in the console output distinguishes it from a well-supported one.
This is the procedure for finding out which you have. It changes what the rest of the work costs, so run it before committing deep-research effort, not after — it is a prioritization gate, not a post-hoc note.
Reaching the records is the aop-wiki skill's job — read it for the CLI, the
date footgun, and the entity shapes. This skill is what you do with a KER once
you have one.
The 29.41% rule
completion_score.percent == 29.41 on a KER means the record is an empty stub:
endpoints and identifiers, nothing else. This is exact, not a heuristic. In the
08-06-2026 snapshot 1,536 of 2,369 KERs (65%) sit at that value and zero of
them carry a single reference. It is also the corpus median, so most of
AOP-Wiki's causal edges are assertions with nothing behind them.
One number, read before anything else, tells you whether the KER has content. A stub KER is not disqualified — but it means AOP-Wiki is contributing a hypothesis and no evidence, and every citation will have to be found from scratch. Rank the work accordingly, and say so when you report the plan.
The evidence fields
For each KER you are assessing, read three fields on ker_info and one on its
parent AOP:
| Field | On | What it tells you |
|---|---|---|
references |
KER | whether any literature is attached to this edge |
weight_of_evidence.free_text |
KER | whether anyone assessed the edge |
empirical_support.free_text |
KER | whether experimental support is described |
oecd_status |
AOP | whether the pathway was ever externally reviewed |
Three traps live here.
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 · 114 lines · 115 tokens per session scan A cd07e2a94572
ker-evidence-triage is a skill published in the GitHub repository monarch-initiative/dismech (60 stars, last pushed today), licensed BSD-3-Clause. It adds 115 tokens to every session and 1,438 once invoked, about $0.0006 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 2026-09-03.
Other skills, from other repositories
dosdp-design-patterns
Skills for understanding and applying DOSDP (Dead Simple Ontology Design Patterns) to ensure consistent ontology term creation and maintenance. This skill is about recognizing patterns and ensuring consistency, not using dosdp-tools directly.
robot-obo-tool
Skills for using ROBOT, the OBO ontology command-line toolkit for reasoning, template-based term creation, quality control, format conversion, and ontology manipulation. Use this when working with OWL/OBO ontologies that need automated processing.
editing-obo-ontologies
Skills and tools for editing OBO format ontologies, including querying terms, checking out/checking in individual terms, and following OBO format conventions. Do not use this if the source for the ontology you are editing is not in obo format (e.g. ofn).
ontology-access-kit
Skills for querying ontologies using the Ontology Access Kit (OAK). This should only be used for complex ontology operations, for basic external ontology searching use the OLS MCP.
cuopt-numerical-optimization-formulation
LP, MILP, QP — concepts, problem-text parsing, and formulation patterns (parameters, constraints, decisions, objective). Concepts only; no API.
nemo-mbridge-perf-expert-parallel-overlap
Validate and use MoE expert-parallel communication overlap in Megatron-Bridge, including overlapmoeexpertparallelcomm, delaywgradcompute, and flex dispatcher backends such as DeepEP and HybridEP.