agora: Skill for Claude Code

.claude/skills/stress-claim/SKILL.md

stress-claim is a skill for Claude Code from DanceNitra/agora. It costs 191 tokens per session (2,051 once invoked), scanned A, original, MIT.

A review workflow that challenges a claim or finding before it is published or used as a foundation for further work. It examines overstatement, counterarguments, novelty, and blind spots, then gives a publish, reframe, or kill verdict.

In plain words
What is it for?
For red-teaming research claims, hypotheses, public posts, and major conclusions before release or implementation.
Why use it?
It helps catch weak reasoning and unsupported conclusions before other people rely on them or criticize them.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter.

This is DanceNitra/agora's own configuration. It tells Claude Code how to work on agora itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything agora configures →

Reuse

Borrowing it

Nothing to install: this file belongs to DanceNitra/agora. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/DanceNitra/agora/main/.claude/skills/stress-claim/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/DanceNitra/agora

Made for: Claude Code.

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 stress-claim

README.md
[![agentmods](https://agentmods.dev/badge/skills/dancenitra/agora/stress-claim/github.svg)](https://agentmods.dev/skills/dancenitra/agora/stress-claim)
Your own site
<a href="https://agentmods.dev/skills/dancenitra/agora/stress-claim"><img src="https://agentmods.dev/badge/skills/dancenitra/agora/stress-claim/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 stress-claim

Your own site · 80×15
<a href="https://agentmods.dev/skills/dancenitra/agora/stress-claim"><img src="https://agentmods.dev/badge/skills/dancenitra/agora/stress-claim.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 191 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,051 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.
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 $0.00191 $0.02051
Opus 5 $0.00096 $0.01026
Sonnet 5 $0.00038 $0.00410
Haiku 4.5 $0.00019 $0.00205

Measured 10d ago against content hash 69b69048f3dd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

stress-claim 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 10d 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.

.claude/skills/stress-claim/SKILL.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Stress-Claim — adversarially red-team our own claim before we ship it

What this does

Takes ONE of our claims (a Crucible verdict, a flagship thesis, a hypothesis, a post draft) and attacks it the way a hostile expert would, before we publish or build on it. Where verify-claims checks whether the cited facts are true, this checks whether the argument holds: is it actually novel or a textbook re-derivation, does it overclaim past the evidence, what is the strongest counter, and what is the blind spot no lens addressed. It returns a blunt verdict — PUBLISH / REFRAME / KILL — with the exact fixes. The goal is to find why we're wrong before a sharp audience does (the breakthrough scan killed 5/6 candidates this way; the nudging/G2G confounds were caught this way).

Self-contained: built-in Agent (general-purpose), WebSearch/WebFetch. No external services. ~5-7 agents.

When to use (before, not after)

Run it BEFORE: recording a Crucible REPRODUCED/FAILED verdict, shipping a flagship/canon claim, opening a gated outreach that asserts a finding, or committing to build on a result. Pairs with verify-claims (facts) — run both before any flagship publish; this one is the argument/credibility half.

PRE-DRAFT MODE — the default for a new article (owner, PERMANENT 2026-08-17)

"pred publikovanim noveho clanku pusti skeptika dopredu." For anything NEW — an article, a post, a Crucible entry, a first-contact reply — run this before the draft exists, on the claim and its measurement rather than on prose. Skip Phase 2's full panel; run these three, in one message:

  • SHOULD-THIS-EXISTIs {CLAIM} textbook, already published, or already stated by the party we are writing to? Search the literature AND, if there is a target repo/thread, ITS OWN issue tracker and prior comments. Return: NEW / TEXTBOOK-CITE-IT / ALREADY-SAID-BY-THEM, with the source.
  • COUNTER-MEASUREMENT — hand it the probe and the target, never the draft: Re-run this measurement hostilely and try to refute the number. Is the criterion narrower than the property? Is any comparison a tautology? Did the harness create the state it reports?
  • ON-FRONTIERDoes {CLAIM} advance the owner's standing priorities, scored with the SAME board_priority_terms the gates use — not by eye?

Read the full file on GitHub · 92 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. 10d ago First seen · 92 lines · 191 tokens per session scan A 69b69048f3dd

Subscribe to this mod's changes

stress-claim is a skill published in the GitHub repository DanceNitra/agora (3 stars, last pushed today), licensed MIT. It adds 191 tokens to every session and 2,051 once invoked, about $0.0010 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.