agentmods.dev

dashclaw-postcommit

A post-commit review command for the DashClaw project. It sends the pending changes through testing, consistency checks, and security review.

In plain words
What is it for?
Running linting, tests, builds, contract checks, drift audits, and reviews of authentication, API keys, webhooks, database queries, and secrets.
Why use it?
It catches failed checks, outdated counts or versions, and security problems after a commit before the changes are treated as safe.

Command for Claude Code

296 3d ago A scan 31 tokens original MIT
View the source file ucsandman/DashClaw
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.

agentmods
npx agentmods add commands/ucsandman/dashclaw/dashclaw-postcommit
Clone the repo
git clone --depth 1 https://github.com/ucsandman/DashClaw

Made for: Claude Code.

Per session 31 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 346 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00031 $0.00346
Opus 5 $0.00015 $0.00173
Sonnet 5 $0.00006 $0.00069
Haiku 4.5 $0.00003 $0.00035

Measured yesterday against content hash e23655c9d7b3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dashclaw-postcommit 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 yesterday.

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/commands/dashclaw-postcommit.md · 27 lines

What it actually says

Dispatch these three subagents IN ONE MESSAGE so they run concurrently. Each agent definition carries its own model:; do not override it.

  1. dashclaw-gate-runner — "Run the DashClaw verification gates (lint, full vitest, build, and the contract checks if routes/SDK/schema changed) and report only failures plus a pass/fail verdict. $ARGUMENTS"
  2. dashclaw-drift-auditor — "Audit the drift-prone counts and the unified version against live truth. Scope of change: the pending changes on the current branch (use git diff/status to find them). $ARGUMENTS"
  3. dashclaw-security-reviewer — "Security-review the pending changes on the current branch (use git diff/status to find them). Focus on the DashClaw auth / API-key / x402 / webhook / repository-SQL / secrets surface. $ARGUMENTS"

When all three return, produce ONE combined verdict:

  • PASS only if all three passed. Otherwise FAIL.
  • List every failure with file:line and which agent found it.
  • Do not summarize passing output; do not paste logs.
  • If any agent errored or failed to authenticate rather than completing, say so loudly and count the wave as FAIL — a skipped review is not a passed review.
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. yesterday First seen · 27 lines · 31 tokens per session scan A e23655c9d7b3

Subscribe to this mod's changes

dashclaw-postcommit is a command published in the GitHub repository ucsandman/DashClaw (296 stars, last pushed 3d ago), licensed MIT. It adds 31 tokens to every session and 346 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 2026-08-30.

Code reviewSecurityTestingagent-frameworkagent-governanceagent-runtimeai-agentsai-infrastructureai-ops
Related

Other commands, from other repositories

code-review

Provide a code review for the given pull request.

inclusionAI/AWorld · 0 tokens

echo

This is a placeholder command definition for plugin framework tests.

inclusionAI/AWorld · 0 tokens

align

Context-aware alignment. When in plan mode, it reviews the active plan. Otherwise, it reviews all branch changes against Ion quality gates and principles, implements the fixes and commits them after operator approval.

dsswift/ion · 39 tokens

create-issue

Open a GitHub issue on the Ion engine repo for a bug or feature request derived from the current conversation, with consumer project details scrubbed.

dsswift/ion · 29 tokens

squash

Rebuild a feature branch into clean conventional commits while preserving its exact final tracked tree.

dsswift/ion · 17 tokens

create-pr

Push the current branch and open a pull request into main with a structured description derived from the branch's commits and issue references.

dsswift/ion · 25 tokens