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.
npx skills add zapgun-ai/clawback --skill watch-errorsgit clone --depth 1 https://github.com/zapgun-ai/clawbackWrote 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/skills/zapgun-ai/clawback/watch-errors)<a href="https://agentmods.dev/skills/zapgun-ai/clawback/watch-errors"><img src="https://agentmods.dev/badge/skills/zapgun-ai/clawback/watch-errors/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/skills/zapgun-ai/clawback/watch-errors"><img src="https://agentmods.dev/badge/skills/zapgun-ai/clawback/watch-errors.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 | $0.00194 | $0.01472 |
| Opus 5.5 | $0.00078 | $0.00589 |
| Sonnet 5.5 | $0.00039 | $0.00294 |
| Haiku 4.5 | $0.00019 | $0.00147 |
Grade A, and why
watch-errors 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 1mo 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 101 lines · 194 tokens per session scan A ab5765545c10
watch-errors is a skill published in the GitHub repository zapgun-ai/clawback (4 stars, last pushed 4mo ago), with no licence file. It adds 194 tokens to every session and 1,472 once invoked, about $0.0008 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 2026-08-31.
Other skills, from other repositories
tang-rou
Ative TANG-ROU (Soft Mist) quando o usuário nomear TANG-ROU ou pedir desenvolvimento, correção, auditoria, otimização ou planejamento de Foundry VTT e programação aplicada: macros, módulos, sistemas, CSB, Combat Tracker Dock, Midi-QOL, DAE, Sequencer, Warp Gate, Active Effects, hooks, compêndios, fichas homebrew, erro…
pwp-debug
Systematic debugging protocol — diagnose, isolate, and fix bugs with discipline. Use this skill whenever the user reports a bug, error, crash, or unexpected behavior. Also use when they say things like 'this is broken', 'not working', 'something's wrong', 'fix this', 'why is this failing', or share an error message or…
pwp-perf
Performance optimization protocol — measure first, optimize second, verify always. Use this skill whenever the user reports something is slow, asks about performance, wants to optimize, or mentions load times, bundle size, rendering speed, memory usage, or database query performance. Also use when they say 'this is…
shiny-py-optimize
Diagnose and fix performance problems in Shiny for Python apps — slow startup, sluggish interactions, blocking operations, and apps that struggle beyond a handful of concurrent users. Use when a Shiny for Python app is slow, hangs, recomputes too much, times out, or must support more users; when the user asks to…
tidewave-integration
Tidewave MCP runtime tools — debugging, smoke testing, live state inspection, SQL queries, hex docs. Use when evaluating code in a running Phoenix app.
perf
Use when anything in a Phoenix app is slow, times out, or uses too much memory, even if the cause looks obvious. Load it before analyzing or fixing: it runs measured Ecto, LiveView and OTP checks and ranks fixes.