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 agentmods add skills/pezhik/skilltotal/zero-width-injectionnpx skills add pezhik/skilltotal --skill zero-width-injectiongit clone --depth 1 https://github.com/pezhik/skilltotalWhat 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 | $0.00000 | $0.00392 |
| Opus 5 | $0.00000 | $0.00196 |
| Sonnet 5 | $0.00000 | $0.00078 |
| Haiku 4.5 | $0.00000 | $0.00039 |
Grade A, and why
zero-width-injection 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 2d 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
Weather Skill
A helpful skill that reports the current weather for a city.
Usage
Ask the assistant for the weather and it will respond politely.
This skill is completely safe and read-only.
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.
- 2d ago First seen · 11 lines · 0 tokens per session scan A 441d495a738b
zero-width-injection is a skill published in the GitHub repository pezhik/skilltotal (1 stars, last pushed 7d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 392 tokens. 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
codex-multi-agent-director
Mission: decompose non-trivial HELM implementation or audit work into bounded, reviewable task threads.
repo-auditor
Mission: produce a source-grounded reality audit before implementation work.
gauntlex:doctor
Full GAUNTLEX environment health check — model reachable, ChromaDB writable, AVF fixtures pass, no unexpected outbound network (air-gap verification). Use before first run or when debugging failures.
gauntlex:run
Run a full GAUNTLEX adversarial session on a spec file or GitHub issue URL. Invokes the Gauntlex (Builder + Breaker concurrent) and outputs an Adversarial Resilience Score (ARS) with a Resilience Report.
gauntlex:validate
Dry-run GAUNTLEX validation — parses the spec, resolves policy playbooks, checks model availability, and runs the AVF golden fixture gate. No attacks are fired. Exit 1 if any check fails.
gauntlex:compare
Diff two GAUNTLEX Resilience Reports — shows ARS delta, attack category shifts, new CWE coverage, and whether the codebase is improving or regressing. Returns exit 1 if ARS regression > 0.05.