agentmods.dev

agent-watchdog

agent-watchdog is a skill for Claude Code from Team-Deepiri/deepiri-axiom. It costs 58 tokens per session (640 once invoked), scanned A, original, Apache-2.0.

A review assistant for checking another coding agent's session, transcript, code changes, pull request, branch, logs, or summary against the original request.

In plain words
What is it for?
Use it to audit completed work, monitor a running task, compare multiple agent runs, and identify or fix clear gaps after checking the evidence.
Why use it?
It helps find missing requirements, weak verification, and unsupported claims instead of relying on an agent's final summary. It can watch, compare, report gaps, or make narrow fixes when authorized.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the TodoWrite tool.

not rated 2repo yesterday A scan 58 tokens original Apache-2.0

Good fit Use it to audit completed work, monitor a running task, compare multiple agent runs, and identify or fix clear gaps after checking the evidence.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/team-deepiri/deepiri-axiom/agent-watchdog
View source ↗ Team-Deepiri/deepiri-axiom
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.

Any agent
npx skills add Team-Deepiri/deepiri-axiom --skill agent-watchdog
Clone the repo
git clone --depth 1 https://github.com/Team-Deepiri/deepiri-axiom

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 agent-watchdog

README.md
[![agentmods](https://agentmods.dev/badge/skills/team-deepiri/deepiri-axiom/agent-watchdog/github.svg)](https://agentmods.dev/skills/team-deepiri/deepiri-axiom/agent-watchdog)
Your own site
<a href="https://agentmods.dev/skills/team-deepiri/deepiri-axiom/agent-watchdog"><img src="https://agentmods.dev/badge/skills/team-deepiri/deepiri-axiom/agent-watchdog/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 agent-watchdog

Your own site · 80×15
<a href="https://agentmods.dev/skills/team-deepiri/deepiri-axiom/agent-watchdog"><img src="https://agentmods.dev/badge/skills/team-deepiri/deepiri-axiom/agent-watchdog.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 640 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 $0.00058 $0.00640
Opus 5.5 $0.00023 $0.00256
Sonnet 5.5 $0.00012 $0.00128
Haiku 4.5 $0.00006 $0.00064

Measured 11d ago against content hash 42987942e326, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

agent-watchdog 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 11d 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.

skills/agent-watchdog/SKILL.md · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent watchdog

Reviewer with a pager: wait for completion when needed, reconstruct the request, verify evidence, close the gap between ask and outcome.

Source: BuilderIO/skills (agent-watchdog). MIT.

Modes

  • Watch only — monitor until terminal state; no edits
  • Audit — gap report from prompt/transcript/diff/tests/CI; no edits
  • Audit and fix — audit first, then narrow fixes for clear gaps
  • Compare — multiple sessions/agents against the same original request

If authority is unclear, default to audit-only and say what you would fix.

Resolve the target

  1. Identify artifacts: session ID, transcript, PR, branch, CI, pasted summary
  2. Prefer the most direct source over summaries
  3. If still running and user asked to watch, poll until done/blocked/stale
  4. If unresolvable, ask for the missing identifier

Reconstruct the contract

  • Original request and later scope changes
  • Explicit constraints (branch, no-edit, validation, security)
  • Implied acceptance criteria (behavior, tests, CI, docs, screenshots)
  • Other agent's final claims and caveats

User request is source of truth — not the other agent's summary.

Audit evidence

  • Changed files + relevant neighbors
  • git status/diff without reverting unrelated work
  • Claimed commands vs actual output when available
  • Failed/skipped tests, CI, screenshots, review threads
  • UI: prefer screenshots/browser over prose claims

Classify: Gap | Bug | Verification miss | Scope drift | No issue

Fix narrowly (when authorized)

  1. Only clear-evidence gaps
  2. Preserve unrelated local changes; no branch moves unless asked
  3. Existing patterns + targeted tests
  4. Smallest validation after each meaningful fix
  5. Stop for product decisions, credentials, destructive or broad rewrites

Report

Status
- Done, blocked, stale, or still running.

Requested
- What the user asked the watched agent to do.

Observed
- What changed, claimed, and verified.

Gaps
- Missing behavior, bugs, weak verification, or scope drift.

Fixes made
- Files changed and validation. Omit for audit-only.

Remaining risk
- Still unverified or waiting on CI/review/human.

Read the full file on GitHub · 86 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. 11d ago First seen · 86 lines · 58 tokens per session scan A 42987942e326

Subscribe to this mod's changes

agent-watchdog is a skill published in the GitHub repository Team-Deepiri/deepiri-axiom (2 stars, last pushed yesterday), licensed Apache-2.0. It adds 58 tokens to every session and 640 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-26.

Code reviewDebugging
Related

agent-watchdog compared with skills from other repositories

agent-watchdog next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
agent-watchdogTeam-Deepiri/deepiri-axiomSkill2yesterdayApache-2.0A58Claude Code
sync-bridgechromium/chromiumSkill25kyesterdayBSD-3-ClauseA109Claude Code, Codex
sync-model-processorchromium/chromiumSkill25kyesterdayBSD-3-ClauseA98Claude Code, Codex
adversarial-revieweremdash-cms/emdashSkill14kyesterdayMITA72Claude Code, Codex
gsd-ns-reviewopen-gsd/gsd-coreSkill11kyesterdayMITA16Claude Code
gitnexushashgraph-online/awesome-codex-pluginsSkill1.5kyesterdayApache-2.0A58Codex
issuejeremylongshore/tons-of-skills-marketplaceSkill2.9kyesterdayMITA115Claude Code