claude-code-channels: Agent for Claude Code

.claude/agents/pre-push-reviewer.md

pre-push-reviewer is an agent for Claude Code from osisdie/claude-code-channels. It costs 39 tokens per session (987 once invoked), scanned A, original, MIT.

An automated pre-push review that checks a project's documentation, security-sensitive changes, commit messages, and required README or changelog updates before code is sent to a remote repository.

In plain words
What is it for?
Running markdown lint, scanning the outgoing diff for credentials, checking conventional commit rules, and verifying README and CHANGELOG updates.
Why use it?
It catches common release-blocking problems, such as markdown errors or accidentally committed secrets, before pushing.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

This is osisdie/claude-code-channels's own configuration. It tells Claude Code how to work on claude-code-channels 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 claude-code-channels configures →

Reuse

Borrowing it

Nothing to install: this file belongs to osisdie/claude-code-channels. 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/osisdie/claude-code-channels/main/.claude/agents/pre-push-reviewer.md
Clone the repo
git clone --depth 1 https://github.com/osisdie/claude-code-channels

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 pre-push-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/osisdie/claude-code-channels/pre-push-reviewer.svg)](https://agentmods.dev/agents/osisdie/claude-code-channels/pre-push-reviewer)
Your own site
<a href="https://agentmods.dev/agents/osisdie/claude-code-channels/pre-push-reviewer"><img src="https://agentmods.dev/badge/agents/osisdie/claude-code-channels/pre-push-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 39 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 987 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 $0.00039 $0.00987
Opus 5 $0.00019 $0.00494
Sonnet 5 $0.00008 $0.00197
Haiku 4.5 $0.00004 $0.00099

Measured 8d ago against content hash 41214395a44b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

pre-push-reviewer 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 8d 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/agents/pre-push-reviewer.md · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Pre-Push Code Reviewer

You are a pre-push gate agent. Before code is pushed to remote, you validate all of the following checks. If ANY check fails, clearly report the failures and exit with a non-zero status.

Run ALL checks before reporting -- do not short-circuit on first failure.

1. Lint (Markdown)

bunx markdownlint-cli2 "**/*.md" 2>&1
  • Config lives in .markdownlint-cli2.jsonc at project root
  • Must exit 0 with no violations

2. Security Scan

Check for accidentally committed secrets in the diff (commits about to be pushed):

MAIN=$(git symbolic-ref refs/remotes/origin/HEAD 2>/dev/null | sed 's@refs/remotes/origin/@@' || echo main)
git diff "$MAIN"...HEAD -- . ':!*.lock' ':!node_modules' ':!.venv'

Flag if the diff contains any of:

  • Hardcoded API keys or tokens (patterns: AIza, sk-, ghp_, glpat-, xoxb-, xapp-, Bearer ey)
  • Bot tokens (Telegram: \d+:AA[A-Za-z0-9_-]+, Discord: long base64-ish strings)
  • Password literals (e.g. password = "..." with actual values, NOT env-var references)
  • Private keys (-----BEGIN (RSA |EC )?PRIVATE KEY-----)
  • .env file contents committed directly

Ignore:

  • References to env vars (os.environ, process.env.XXX, $VARIABLE)
  • Documentation examples with placeholder values (xoxb-your-token, <YOUR_TOKEN>, sk-...)
  • Test fixtures with obviously fake values (test123, changeme, example.com)
  • Lock files, node_modules, .venv

3. Conventional Commits

Validate all commits being pushed (not yet on remote):

MAIN=$(git symbolic-ref refs/remotes/origin/HEAD 2>/dev/null | sed 's@refs/remotes/origin/@@' || echo main)
git log "$MAIN"..HEAD --format="%H %s"

Each commit message must:

  • Follow conventional commit format: type(scope?): description
    • Valid types: feat, fix, refactor, docs, style, test, ci, chore, perf, build, revert
  • NOT mention AI model names anywhere in the message body or subject:
    • Forbidden patterns (case-insensitive): claude, gpt, openai, anthropic, gemini, copilot
    • Includes Co-Authored-By trailers referencing any AI model
  • Be in English (commit subject line)

Read the full file on GitHub · 118 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. 8d ago First seen · 118 lines · 39 tokens per session scan A 41214395a44b

Subscribe to this mod's changes

pre-push-reviewer is an agent published in the GitHub repository osisdie/claude-code-channels (5 stars, last pushed 5mo ago), licensed MIT. It adds 39 tokens to every session and 987 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 2026-08-31.

Related

Other agents, from other repositories

refactor-cleaner

Dead code cleanup and consolidation specialist. Use PROACTIVELY for removing unused code, duplicates, and refactoring. Runs analysis tools (knip, depcheck, ts-prune) to identify dead code and safely removes it.

affaan-m/ECC · 51 tokens

git-commit-agent

A dispatchable committer for when direct access to the scopedgitcommit placeable isn't available — verifies a supplied pathspec, commits via the sanctioned scoped route. NOT the default EM commit path: an EM that can reach scopedgitcommit directly should do so (20ms) rather than pay a full dispatch (25s / 24.7k…

dbc-oduffy/coordinator-claude · 98 tokens

task-executor

Use this agent to execute a single tracked task with TDD, commit, and PR creation in an isolated git worktree. Dispatched by /coco:loop for parallel execution. Context: Multiple tasks are ready with non-overlapping file ownership. /coco:loop dispatches parallel agents. assistant: "I'll dispatch task-executor agents…

skullninja/coco-workflow · 97 tokens

author-code-review

Fetches open PRs, reads review comments (including CoderabbitAI), identifies actionable code changes, implements fixes, and pushes commits.

openshift-online/gcp-hcp · 32 tokens

trailhead-executor

trailhead execute subagent: implements an approved PLAN with atomic conventional commits (each carrying a Refs: # trailer).

ToRvaLDz/trailhead · 32 tokens

git-policy-auditor

Audit a repository against the git-management policy and produce a compliance report plus a ready-to-apply migration plan. Read-only — it inspects and proposes, never mutates. Use when asked to "audit against the git policy", "check git-policy compliance", or "plan the git-flow migration for ".

gf-labs/claude-toolbox · 72 tokens