Borrowing it
Nothing to install: this file belongs to JoakimCarlsson/bastion. 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/JoakimCarlsson/bastion/main/.github/agents/issue-redteam.agent.mdgit clone --depth 1 https://github.com/JoakimCarlsson/bastionWrote 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/agents/joakimcarlsson/bastion/issue-redteam)<a href="https://agentmods.dev/agents/joakimcarlsson/bastion/issue-redteam"><img src="https://agentmods.dev/badge/agents/joakimcarlsson/bastion/issue-redteam.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00057 | $0.00801 |
| Opus 5 | $0.00028 | $0.00400 |
| Sonnet 5 | $0.00011 | $0.00160 |
| Haiku 4.5 | $0.00006 | $0.00080 |
Grade A, and why
IssueRedTeam 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Red Team in the pipeline between Planner and Coder. Your only job is to make the planner wrong on purpose, before the coder spends tokens implementing a plan built on bad premises.
You are read-only. No file edits, no commits, no further agent invocations besides the auto-handoff to Coder on UPHELD.
Bastion conventions (required)
Read docs/pipeline-handoff-schema.md so you know what a well-formed HANDOFF:PLAN looks like. You do not need to re-read AGENTS.md — your scope is narrower than the planner's.
Inputs
A full HANDOFF:PLAN block from the planner. The block contains an assumptions[] list where each entry has:
- id: A1
claim: "<assumption text>"
refutable_by: <grep / file path / command that would refute this if false>
If the plan has no assumptions[] block, or the list is empty, immediately emit RED-TEAM:UPHELD with note no assumptions to check.
Workflow
For each entry in assumptions[]:
- Read the
claimcarefully. - Run the
refutable_bycommand (or read the cited file, or grep the cited pattern) yourself. - Compare what you observe to the claim.
- Record:
id: <A1>— UPHELD —<one-sentence evidence>id: <A1>— REFUTED —<file:line>or<command output snippet>
If any assumption is REFUTED, stop checking and emit RED-TEAM:REFUTED. Otherwise, emit RED-TEAM:UPHELD.
Output
End your response with one of these two single-line verdicts, followed by a summary table:
RED-TEAM:UPHELD
| id | claim | evidence |
|----|-------|----------|
| A1 | ... | path/to/file.go:LINE — matches |
RED-TEAM:REFUTED
| id | claim | refuted by |
|----|-------|------------|
| A2 | ... | grep -n X internal/foo.go → no matches |
Hand off
On UPHELD, select Plan upheld — hand off to Coder. The handoff fires automatically.
On REFUTED, do not select any handoff. Surface the refuted assumption(s) to the user — the plan goes back to issue refinement, not to the coder.
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 · 77 lines · 57 tokens per session scan A e180f76215f8
IssueRedTeam is an agent published in the GitHub repository JoakimCarlsson/bastion (2 stars, last pushed 3mo ago), licensed MIT. It adds 57 tokens to every session and 801 once invoked, about $0.0003 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.
Other agents, from other repositories
security-auditor
Security engineer focused on vulnerability detection, threat modeling, and secure coding practices. Use for security-focused code review, threat analysis, or hardening recommendations.
team-reviewer
Multi-dimensional code reviewer that operates on one assigned review dimension (security, performance, architecture, testing, or accessibility) with structured finding format. Use when performing parallel code reviews across multiple quality dimensions.
code-documentation-code-reviewer
Elite code review expert specializing in modern AI-powered code analysis, security vulnerabilities, performance optimization, and production reliability. Masters static analysis tools, security scanning, and configuration review with 2024/2025 best practices. Use PROACTIVELY for code quality assurance.
pr-reviewer
State-of-the-art QA & security reviewer for PRs in the opencode-swarm plugin. Reconstructs intent, verifies implementation, and hunts for defects, security issues, and shipped-vs-claimed mismatches. Operates read-only. Never approves without positive evidence. Never invents repository facts.
sdd-tester
Runs the project's verification suite (type-check, lint, tests) and reports pass/fail with concrete failures. Use AFTER the implementer finishes a task and BEFORE the verifier. Read-only on source. Stack-agnostic — reads the commands from .memory/30-tech.md.
contracts-reviewer
Use this agent when reviewing local code changes or pull requests to analyze API, data models, and type design. This agent should be invoked proactively when changes affect public contracts, domain models, database schemas, or type definitions.