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.
git clone --depth 1 https://github.com/permanu/superskillWrote 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/commands/permanu/superskill/watchdog)<a href="https://agentmods.dev/commands/permanu/superskill/watchdog"><img src="https://agentmods.dev/badge/commands/permanu/superskill/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.
<a href="https://agentmods.dev/commands/permanu/superskill/watchdog"><img src="https://agentmods.dev/badge/commands/permanu/superskill/watchdog.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00016 | $0.00200 |
| Opus 5.5 | $0.00006 | $0.00080 |
| Sonnet 5.5 | $0.00003 | $0.00040 |
| Haiku 4.5 | $0.00002 | $0.00020 |
Grade A, and why
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 10d 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.
What it actually says
Run a superskill watchdog pass. Input: $ARGUMENTS (empty = dig the latest session).
- Call the superskill MCP tool
watchdogwith action "dig" and the scope implied by the input (session | window --since 7d | env | all). Default: session. - Read catalog/watchdog/dig.md and follow it: verify every finding against this repo before proposing anything; present findings most-severe-first with evidence and a concrete proposal.
- For steering/guardrail findings, make the edits yourself (navigation pointers; deterministic checks over prose rules). For mechanical reclamation, call
watchdog fix— dry-run first,--applyonly after I confirm. - Close the loop: mark what changed with
watchdog fix --finding <id> --apply(or --dismiss).
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.
- 10d ago First seen · 11 lines · 16 tokens per session scan A 1d8775802da8
watchdog is a command published in the GitHub repository permanu/superskill (17 stars, last pushed 2d ago), licensed Apache-2.0. It adds 16 tokens to every session and 200 once invoked, about $0.0001 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 2026-10-05.
Other commands, from other repositories
ui-aqa-flow-test-report-analysis
Phase 7 Test Report Analysis of ui-aqa-flow.
api-aqa-flow-execution-and-report-analysis
Phase 6 Execution & Report Analysis of api-aqa-flow (USER INTERACTION REQUIRED).
api-aqa-flow-test-correction
Phase 7 Test Corrections of api-aqa-flow (USER APPROVAL REQUIRED).
ui-aqa-flow-test-correction
Phase 8 Test Correction of ui-aqa-flow.
doctor
Run IJFW health check (files, MCP server, hooks, memory, caps, framing).
ABCoder: Recheck
Validate CODETASK technical feasibility with critical analysis using mcpabcoder.