simulation-triage

simulation-triage is a skill for Claude Code, Codex from chipweaver/veripower. It costs 36 tokens per session (2,423 once invoked), scanned A, original, MIT.

A failure-analysis guide for simulation pipelines. It determines which stage or input caused a failed simulation and records the evidence for that judgment.

In plain words
What is it for?
Use it after a simulation fails to identify who is responsible, where the failure occurred, and what evidence supports the decision; it is not for fixing code or rerunning regression tests.
Why use it?
It prevents the wrong part of a multi-stage workflow from being rebuilt after a failure. It also protects canonical outputs belonging to other stages.

Skill for Claude CodeCodex

Part of the veripower plugin — 12 skills, 3 hooks shipped together

Install

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.

agentmods
npx agentmods add skills/chipweaver/veripower/simulation-triage
Any agent
npx skills add chipweaver/veripower --skill simulation-triage
Clone the repo
git clone --depth 1 https://github.com/chipweaver/veripower

Made for: Claude Code, Codex.

Or install veripower, the plugin that ships this one along with the rest of its 12 skills, 3 hooks.

Wrote 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.

agentmods badge for simulation-triage

README.md
[![agentmods](https://agentmods.dev/badge/skills/chipweaver/veripower/simulation-triage.svg)](https://agentmods.dev/skills/chipweaver/veripower/simulation-triage)
Your own site
<a href="https://agentmods.dev/skills/chipweaver/veripower/simulation-triage"><img src="https://agentmods.dev/badge/skills/chipweaver/veripower/simulation-triage.svg" alt="Measured on agentmods" height="20"></a>
Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,423 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00036 $0.02423
Opus 5 $0.00018 $0.01211
Sonnet 5 $0.00007 $0.00485
Haiku 4.5 $0.00004 $0.00242

Measured 5d ago against content hash ee80b5d5e137, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

simulation-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 5d ago.

The scan reads SKILL.md. This mod also ships 3 executable files (scripts/simtriage/__init__.py, scripts/simtriage/__main__.py, scripts/simtriage/result.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/simulation-triage/SKILL.md · 161 lines

How it starts

The opening of the file, as written. The whole thing — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Simulation Triage

A simulation run failed and the pipeline cannot tell whose fault it is. You produce one judgment: whose, where, and on what evidence. No tool checks that judgment and no downstream stage re-derives it, so what you land is what gets rebuilt.

Iron Rule

  • Canonical read-only, own-workdir writable: read any canonical artifact freely (RTL, spec, TB logs, plan) but never modify another stage's canonical output — RTL, TB, spec, plan, or any other stage's result.json. The only files you write live under your own {workdir}.
  • Scripts are black boxes — never Read their source. Invoke them per this skill's documented command lines (flags via --help); on a non-zero exit act on the documented failure protocol (stderr / FAIL= token / stdout verdict), not the source. Sole exception: debugging a suspected bug in a script itself.

Artifacts

<skill> is this skill's own base directory, named on the first line of this file.

Read {workdir}/dispatch.json first — the kernel writes it at dispatch. Its inputs table maps four keys to absolute cross-stage locations; read those directly and never construct a module-root-relative Verification/… or Design/… path yourself. Throughout this skill, <sim_run> is shorthand for the failed-run directory named by that key (and likewise <design> / <rtl> / <plan>).

Key What it names What you read there
<sim_run> The failed simulation run directory (not that stage's root) result.json, the failing envelope. Read this copy, not the simulation stage root's: the stage root holds whichever run finished last, so a later passing run overwrites it. The run's whole working area is here too — regression log, per-case UVM logs, coverage DB, the TB it compiled, and any retained waveform.
<design> The specification stage root design.md and the per-child <child>.md it indexes, via manifest.json. Read these to judge whether the observed behavior is an RTL defect or an under-specified requirement.
<rtl> The rtl-design stage root The sources listed in rtl-files.json: the DUT under test, and the instance hierarchy inside it.
<plan> The simulation-plan stage root verification-plan.md — what the refmodel and scoreboard are supposed to enforce — and tb-scaffold.json, which owns the testpoint list a coverage hole is measured against.

Read the full file on GitHub · 161 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

  1. 5d ago First seen · 161 lines · 36 tokens per session scan A ee80b5d5e137

Subscribe to this mod's changes

simulation-triage is a skill published in the GitHub repository chipweaver/veripower (4 stars, last pushed 5d ago), licensed MIT. It adds 36 tokens to every session and 2,423 once invoked, about $0.0002 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.