publish-the-run-that-did-not-work

publish-the-run-that-did-not-work is a skill for Claude Code, Codex from brcampidelli/chimera-agent. It costs 38 tokens per session (659 once invoked), scanned A, original, Apache-2.0.

A reporting rule for preserving and publishing an experiment whose result is negative, inconclusive, or does not support the expected claim.

In plain words
What is it for?
Use it when reporting comparisons, experiments, or replications. It helps define failure conditions in advance, report uncertainty with intervals, preserve earlier results, and retract unsupported claims.
Why use it?
It prevents choosing only favorable reruns and hiding inconvenient evidence. Keeping superseded results unchanged makes corrections and failed replications visible.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it when reporting comparisons, experiments, or replications. It helps define failure conditions in advance, report uncertainty with intervals, preserve earlier results, and retract unsupported claims.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/brcampidelli/chimera-agent/publish-the-run-that-did-not-work
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.

Any agent
npx skills add brcampidelli/chimera-agent --skill publish-the-run-that-did-not-work
Clone the repo
git clone --depth 1 https://github.com/brcampidelli/chimera-agent

Made for: Claude Code, Codex.

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 publish-the-run-that-did-not-work

README.md
[![agentmods](https://agentmods.dev/badge/skills/brcampidelli/chimera-agent/publish-the-run-that-did-not-work/github.svg)](https://agentmods.dev/skills/brcampidelli/chimera-agent/publish-the-run-that-did-not-work)
Your own site
<a href="https://agentmods.dev/skills/brcampidelli/chimera-agent/publish-the-run-that-did-not-work"><img src="https://agentmods.dev/badge/skills/brcampidelli/chimera-agent/publish-the-run-that-did-not-work/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.

agentmods 80×15 button for publish-the-run-that-did-not-work

Your own site · 80×15
<a href="https://agentmods.dev/skills/brcampidelli/chimera-agent/publish-the-run-that-did-not-work"><img src="https://agentmods.dev/badge/skills/brcampidelli/chimera-agent/publish-the-run-that-did-not-work.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 659 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 5.1 $0.00038 $0.00659
Opus 5 $0.00019 $0.00329
Sonnet 5 $0.00008 $0.00132
Haiku 4.5 $0.00004 $0.00066

Measured 12d ago against content hash 1b443d67d0a4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

publish-the-run-that-did-not-work 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 12d 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.

skills/publish-the-run-that-did-not-work/SKILL.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Trigger

You ran a comparison to decide whether a change helps, and the result is inconvenient: negative, not significant, or contradicting something already announced.

It does not apply to a run that was simply broken — a crashed harness measured nothing, and publishing it as a result would be its own kind of noise. Fix and rerun, and say that you did.

Do

  1. Write down, before running, what outcome would kill the claim. If you cannot name it, the experiment cannot fail, and an experiment that cannot fail is not one.
  2. Report the effect with an interval, not a point estimate. +9.8pp [−3.5, +16.7] says something +9.8pp does not.
  3. When a later run supersedes an earlier one, keep the earlier one published and unedited, and link the correction. Amending it removes the only evidence that the correction happened.
  4. If a claim does not survive replication, retract it in the same place it was made, in the same size type.

Avoid

Rerunning until it looks better and reporting the best run. That is not a bad measurement, it is a selected one, and selection cannot be detected in the number afterwards by anyone — including you.

Avoid quietly dropping the negative result while keeping the positive one from the same series. Avoid pooling a fresh sample with an old one after seeing that pooling helps; if pooling was not pre-registered as primary, it is secondary and must be labelled that way.

And avoid describing a non-significant delta with words that imply significance: "improved", "lifted", "up from". "Not significant on its own" is the sentence.

Check

Ask what a sceptical reader could conclude from the artefacts you published. If the answer requires trusting that you did not discard anything, the artefacts are incomplete — publish the journal, the per-item outcomes, or the raw pairs.

Then check the claim in your own README against the results section. If one says a thing the other retracts, the retraction is the true one and the claim has to move.

Read the full file on GitHub · 66 lines

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. 12d ago First seen · 66 lines · 38 tokens per session scan A 1b443d67d0a4

Subscribe to this mod's changes

publish-the-run-that-did-not-work is a skill published in the GitHub repository brcampidelli/chimera-agent (25 stars, last pushed today), licensed Apache-2.0. It adds 38 tokens to every session and 659 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 2026-08-30.

Related

Other skills, from other repositories

personal-genomics

Analyse personal DNA / genome files for pharmacogenomics, disease risk, carrier status, ancestry and traits. Use whenever the user mentions DNA or genome analysis, a raw genome file, gene names, drug-gene interactions, or wants to combine multiple DNA sources.

sammcj/agentic-coding · 56 tokens

Jupyter Live Kernel

Guides notebook-first analysis with reproducible kernels, inspectable data loading, and explicit promotion paths back into durable code.

agentic-in/elephant-agent · 29 tokens

arXiv

Search, filter, and summarize arXiv papers with explicit titles, authors, dates, and paper links before drawing conclusions.

agentic-in/elephant-agent · 29 tokens

ml-paper-writing

Write publication-ready ML/AI papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM. Use when drafting papers from research repos, structuring arguments, verifying citations, or preparing camera-ready submissions. Includes LaTeX templates, reviewer guidelines, and citation verification workflows.

raphaelmansuy/edgecrab · 65 tokens

neuroskill-bci

Connect to a running NeuroSkill instance and incorporate the user's real-time cognitive and emotional state (focus, relaxation, mood, cognitive load, drowsiness, heart rate, HRV, sleep staging, and 40+ derived EXG scores) into responses. Requires a BCI wearable (Muse 2/S or OpenBCI) and the NeuroSkill desktop app…

raphaelmansuy/edgecrab · 82 tokens

sparse-autoencoder-training

Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use when discovering interpretable features, analyzing superposition, or studying monosemantic representations in language models.

raphaelmansuy/edgecrab · 58 tokens