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/mie-ker-capture/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/mie-ker-capture)<a href="https://agentmods.dev/skills/monarch-initiative/dismech/mie-ker-capture"><img src="https://agentmods.dev/badge/skills/monarch-initiative/dismech/mie-ker-capture/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/mie-ker-capture"><img src="https://agentmods.dev/badge/skills/monarch-initiative/dismech/mie-ker-capture.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 | $0.00113 | $0.03206 |
| Opus 5 | $0.00056 | $0.01603 |
| Sonnet 5 | $0.00023 | $0.00641 |
| Haiku 4.5 | $0.00011 | $0.00321 |
Grade A, and why
mie-ker-capture 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 6d 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 — 248 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MIE -> KER capture
An AOP Key Event with no dismech counterpart is a curation lead, not a curation task. This is the procedure that turns one into the other: find the edges the Key Event sits on, discard the ones that are not about your disease, and find out how much of the causal claim AOP-Wiki can actually back before you commit to curating it.
Reaching the AOP-Wiki data is the aop-wiki skill's job — read it first for the
CLI, the date footgun, and the entity shapes. This skill is what you do with the
output.
The finding that motivates the whole procedure: a KER can be completely
uncited — most are. 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; ker-evidence-triage carries the measurement.
Step 5 is where you find out, and it belongs before any curation decision, not
after.
Scope — this is the MIE case
The procedure was written for Molecular Initiating Events: a Key Event with
no dismech counterpart sitting at the start of a chain. Its worked examples are
all that shape. The same quality checks would be wanted for a pathway-terminating
Adverse Outcome, or for an intermediate Key Event, and most of this transfers
unchanged — the lookup is direction-agnostic (find-kers-for-events returns both
roles, and Step 4 says how to read each), and the relevance filter, evidence
triage, connected components and literature verification do not care which end
you started from.
Two things do bake in the MIE direction, and are what a future AO or intermediate-KE version would have to revisit:
- Step 6 checks the downstream end against the Step 1 entity. An AO-driven sweep asks the mirror question — is the mechanism leading to this outcome already represented? — so that check would run on the upstream end instead.
- Step 6's curation outcome assumes an entry point: a new node plus a
downstreamedge into existing mechanism. For an Adverse Outcome the new node is terminal, and the edge runs from existing mechanism into it.
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.
- 6d ago First seen · 248 lines · 113 tokens per session scan A 88c9f79d164e
mie-ker-capture is a skill published in the GitHub repository monarch-initiative/dismech (60 stars, last pushed today), licensed BSD-3-Clause. It adds 113 tokens to every session and 3,206 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
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.
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.
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.