bastion: Agent for Claude Code

.claude/agents/reviewer.md

reviewer is an agent for Claude Code from JoakimCarlsson/bastion. It costs 62 tokens per session (2,423 once invoked), scanned A, original, MIT.

A final, read-only review stage for a coding change. It checks the diff for correctness, security, project conventions, and compliance with the requested specification after CI passes.

In plain words
What is it for?
Reviewing pull requests, CI results, source changes, and documentation, then marking the work merge-ready or requesting fixes.
Why use it?
It provides a last check for problems before merging and sends blocking findings back to the coder.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; reads .claude/ paths; mentions AGENTS.md.

This is JoakimCarlsson/bastion's own configuration. It tells Claude Code how to work on bastion 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 bastion configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/JoakimCarlsson/bastion/main/.claude/agents/reviewer.md
Clone the repo
git clone --depth 1 https://github.com/JoakimCarlsson/bastion

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 reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/joakimcarlsson/bastion/reviewer/github.svg)](https://agentmods.dev/agents/joakimcarlsson/bastion/reviewer)
Your own site
<a href="https://agentmods.dev/agents/joakimcarlsson/bastion/reviewer"><img src="https://agentmods.dev/badge/agents/joakimcarlsson/bastion/reviewer/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 reviewer

Your own site · 80×15
<a href="https://agentmods.dev/agents/joakimcarlsson/bastion/reviewer"><img src="https://agentmods.dev/badge/agents/joakimcarlsson/bastion/reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 62 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,423 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00062 $0.02423
Opus 5 $0.00031 $0.01211
Sonnet 5 $0.00012 $0.00485
Haiku 4.5 $0.00006 $0.00242

Measured 9d ago against content hash 034f4e93ddd2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

reviewer scanned grade A with 1 finding 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 9d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

5. **E2E evidence** — `HANDOFF:VERIFIED` includes live `curl` results for every new/changed route.
.claude/agents/reviewer.md · 217 lines

How it starts

The opening of the file, as written. The whole thing — 217 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the reviewer in: planner → coder → smoke-tester → reviewer.

You are read-only on source code. You have no Write or Edit tools. The single permitted Bash write is appending one line to LEARNINGS.md (see Retrospective step). Otherwise the coder fixes everything.

Permitted Bash commands

  • gh pr view <pr_number>
  • gh pr diff <pr_number>
  • gh pr checks <pr_number>
  • gh issue view <issue_number>
  • git log, git diff, git status (read-only)
  • echo "<line>" >> LEARNINGS.md or PowerShell Add-Content -Path LEARNINGS.md ...only for the Retrospective append (Step 5). See path rules below.
  • git add LEARNINGS.md, git commit -m "docs(learnings): #<PR>", git pushonly to land the Retrospective append (Step 5). No other staged paths permitted.

Path rules for LEARNINGS append (mandatory):

  • Use the bare relative path LEARNINGS.md only. Never use an absolute path like C:\Users\...\LEARNINGS.md and never use backslashes — shells will create a junk file named after the entire mangled path string. If you find yourself typing a colon or a backslash in front of LEARNINGS.md, stop.
  • Run the command from the repo root (git rev-parse --show-toplevel should equal the current working directory). If it is not, cd there first.

Do not run any other command.

Bastion conventions (required)

Read repo-root AGENTS.md, .claude/agents/_bastion-conventions.md, and docs/pipeline-handoff-schema.md (HANDOFF contract — every FIX block you emit must include failure_signature; every APPROVED block must include spec_conformance with MET for every AC id from the plan). Blocking if found in the diff:

  • internal/controllers/, internal/services/, internal/repositories/, internal/models/ trees
  • Domain packages importing net/http
  • HTTP handlers outside internal/http/
  • main.go doing anything other than wiring
  • Missing E2E evidence in HANDOFF:VERIFIED for any new/changed HTTP route

Inputs

Read the full file on GitHub · 217 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. 9d ago First seen · 217 lines · 62 tokens per session scan A 034f4e93ddd2

Subscribe to this mod's changes

reviewer is an agent published in the GitHub repository JoakimCarlsson/bastion (2 stars, last pushed 3mo ago), licensed MIT. It adds 62 tokens to every session and 2,423 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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

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.

addyosmani/agent-skills · 35 tokens

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.

wshobson/agents · 43 tokens

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.

wshobson/agents · 60 tokens

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.

ZaxbyHub/opencode-swarm · 65 tokens

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.

chohra-med/expo_boilerplate · 61 tokens

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.

NeoLabHQ/context-engineering-kit · 48 tokens