challenger-calibration

challenger-calibration is an agent for Claude Code from martineserios/thebrana. It costs 20 tokens per session (1,256 once invoked), scanned A, original, MIT.

A scoring guide for rating the seriousness of findings from the Challenger review agent.

In plain words
What is it for?
Use it to score risks from 1 to 5, apply verdict rules, and handle disagreements between verification reviewers.
Why use it?
It makes review results more consistent by defining severity levels and when a plan should proceed, change, or be reconsidered.

Agent for Claude Code

Written for Claude Code: PreToolUse hook event. Also seen: mentions subagents.

Part of the brana plugin — 56 skills, 4 commands, 14 agents, 13 hooks shipped together

Good fit Use it to score risks from 1 to 5, apply verdict rules…

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/martineserios/thebrana/calibration
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.

Clone the repo
git clone --depth 1 https://github.com/martineserios/thebrana

Made for: Claude Code.

Or install brana, the plugin that ships this one along with the rest of its 56 skills, 4 commands, 14 agents, 13 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 challenger-calibration

README.md
[![agentmods](https://agentmods.dev/badge/agents/martineserios/thebrana/calibration.svg)](https://agentmods.dev/agents/martineserios/thebrana/calibration)
Your own site
<a href="https://agentmods.dev/agents/martineserios/thebrana/calibration"><img src="https://agentmods.dev/badge/agents/martineserios/thebrana/calibration.svg" alt="Measured on agentmods" height="20"></a>
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,256 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 $0.00020 $0.01256
Opus 5 $0.00010 $0.00628
Sonnet 5 $0.00004 $0.00251
Haiku 4.5 $0.00002 $0.00126

Measured 6d ago against content hash c8b55698b610, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

challenger-calibration 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.

system/agents/CALIBRATION.md · 128 lines

How it starts

The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Challenger Calibration

Severity scoring guide with few-shot examples and hard thresholds. Referenced by challenger.md and the /brana:challenge skill.

Scoring Rubric (1-5 Scale)

Score Severity Definition Verdict impact
5 Critical Plan blocks success, causes data loss, or security breach RECONSIDER
4 High Known unmitigated risk affecting real workflows RECONSIDER
3 Medium Solid plan with minor gaps or workarounds needed PROCEED WITH CHANGES
2 Low Plan works, could be simpler or more robust PROCEED WITH CHANGES
1 Clean No findings; plan is solid as stated PROCEED

Verdict rules:

  • ANY finding >= 4 --> verdict is RECONSIDER
  • All findings <= 2 with clear mitigations --> PROCEED WITH CHANGES
  • All findings <= 1 --> PROCEED
  • SPLIT (rung-2 panels only, ADR-082): the verification stage disagreed on a finding. Blocking impact = RECONSIDER for that finding's beat — a SPLIT is never auto-resolved, never counted as FALSE_POSITIVE; it routes to the human valve as its own signal class with both verifier positions attached. Disagreement is diagnostic, not noise (idea doc Round 5 / ADR-082 §4).

Hard Thresholds

CRITICAL (always score 5)

These conditions always trigger critical severity regardless of context:

  1. Service unavailability -- Plan removes a critical feature with zero fallback
  2. Data loss risk -- Migration plan has no backup strategy or rollback mechanism
  3. Workflow breakage -- Change affects >50% of user operations without mitigation
  4. Security/secrets leak -- Plan introduces unencrypted storage of credentials or auth
  5. Untested critical path -- Core assumption (performance, availability) is stated but unvalidated
  6. Dependency conflict -- Plan assumes a library version that conflicts with documented constraints

WARNING (always score 4)

These conditions always trigger warning severity:

Read the full file on GitHub · 128 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. 6d ago First seen · 128 lines · 20 tokens per session scan A c8b55698b610

Subscribe to this mod's changes

challenger-calibration is an agent published in the GitHub repository martineserios/thebrana (3 stars, last pushed yesterday), licensed MIT. It adds 20 tokens to every session and 1,256 once invoked, about $0.0001 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.

Related

Other agents, from other repositories

research-verifier

Citation-integrity verification agent — validates cited URLs, checks file path existence, flags dead links in research briefs. Use during /research Deep mode or when evidence verification is needed. Read-only analysis. Does NOT verify semantic correctness of conclusions (e.g. "this dep is unused") — those require…

pitimon/8-habit-ai-dev · 75 tokens

comment-analyzer

PRFlow review-engine reviewer; use to check code comments match the code before a PR.

The01Geek/prflow · 22 tokens

arn-code-ux-specialist

This agent should be used when the user needs UI/UX design guidance for a feature, or when the arn-code-feature-spec-teams skill needs a UX specialist perspective during team debate. Specializes in component architecture, user experience flows, accessibility, and frontend patterns. Context: Invoked by…

AppsVortex/arness · 237 tokens

backend

Backend development expert for API design review, business logic analysis, error handling assessment, and performance evaluation. Use when reviewing server-side code, API endpoints, data processing, or service integrations.

restarter/lets-workflow · 39 tokens

socrates

A read-only adviser that challenges product-manager decisions as a devil's advocate during review stages. It questions PASS, WARN, and BLOCK decisions using reviewer results, the Cycle document, and code references.

morodomi/dev-crew · 68 tokens

cadence-code-reviewer

Reviews an implementer's diff against repo conventions. Second of two review stages. Runs AFTER cadence-spec-reviewer approves. Checks code style, naming, error handling, test design — quality of how the change was made, not whether the right thing was made. Conflicts with spec-reviewer's findings are resolved by spec…

sentasity/cadence · 70 tokens