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 tomzx/agents --skill audit-compatibilitygit clone --depth 1 https://github.com/tomzx/agentsWrote 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/tomzx/agents/audit-compatibility)<a href="https://agentmods.dev/skills/tomzx/agents/audit-compatibility"><img src="https://agentmods.dev/badge/skills/tomzx/agents/audit-compatibility/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/tomzx/agents/audit-compatibility"><img src="https://agentmods.dev/badge/skills/tomzx/agents/audit-compatibility.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 | $0.00117 | $0.02137 |
| Opus 5.5 | $0.00047 | $0.00855 |
| Sonnet 5.5 | $0.00023 | $0.00427 |
| Haiku 4.5 | $0.00012 | $0.00214 |
Grade A, and why
audit-compatibility 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 22d 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.
How it starts
The opening of the file, as written. The whole thing — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TODAY=!date +%Y-%m-%d
Compatibility Audit (ISO/IEC 25010)
Audits the codebase for compatibility: can the software co-exist with other software and interoperate with it through standards? It finds the things that make two systems conflict over shared resources or fail to communicate cleanly.
This is the Compatibility characteristic of the ISO/IEC 25010 quality model.
Prerequisites
- Working directory is the root of the repository
- Read
.sdlc/context/architecture.mdif present (for integration boundaries) - Package manifest present for dependency-conflict checks (
pyproject.toml,package.json,go.mod,Cargo.toml)
What This Checks
| Sub-characteristic | What it means | Signals scanned |
|---|---|---|
| Co-existence | runs alongside other software without resource or dependency conflict | hardcoded ports/paths/hostnames; well-known shared resources (/tmp, fixed DB names); global mutable state; dependency version conflicts; over-pinned or conflicting transitive deps |
| Interoperability | exchanges data and uses standards correctly | missing API versioning; non-standard content types/charsets; unversioned data formats; missing schema validation on inputs/outputs; brittle string-parsing of external data; incorrect HTTP status codes |
Steps
1. Co-existence: shared resources
Hardcoded ports, hostnames, absolute paths, and well-known shared locations that conflict when two instances or two apps run together:
rg -n "localhost|127\.0\.0\.1|0\.0\.0\.0|:3000|:8080|:5432|:6379|:5672|/tmp/|/var/|/usr/|C:\\\\" -g '*.{py,ts,js,go}' . \
| rg -v "test|spec|example|docs|README"
Flag hardcoded values that should be configurable (env vars, config). Two instances on the same host cannot both bind a hardcoded port or write to a hardcoded path.
Fixed resource names (DB names, queue names, cache keys without a prefix/namespacing):
rg -n "CREATE DATABASE|database=|DB_NAME|queue|exchange|routing_key" -g '*.{py,ts,sql}' .
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.
- 22d ago Changed · +9 lines 29d450c56bed
- 23d ago Changed · +4 lines 929ece35fd54
- 24d ago Changed 09e098bcf710
- 2mo ago First seen · 181 lines · 117 tokens per session scan A 619d0fd03c28
audit-compatibility is a skill published in the GitHub repository tomzx/agents (13 stars, last pushed yesterday), licensed MIT. It adds 117 tokens to every session and 2,137 once invoked, about $0.0005 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
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…