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 redhat-developer/rhdh-skills --skill openspec-audit-changegit clone --depth 1 https://github.com/redhat-developer/rhdh-skillsWrote 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/redhat-developer/rhdh-skills/openspec-audit-change)<a href="https://agentmods.dev/skills/redhat-developer/rhdh-skills/openspec-audit-change"><img src="https://agentmods.dev/badge/skills/redhat-developer/rhdh-skills/openspec-audit-change.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00079 | $0.02003 |
| Opus 5 | $0.00039 | $0.01001 |
| Sonnet 5 | $0.00016 | $0.00401 |
| Haiku 4.5 | $0.00008 | $0.00200 |
Grade A, and why
openspec-audit-change 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 7d 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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Audit an OpenSpec change
Spawn an isolated auditor over one change's artifacts, catch cross-artifact drift before code gets written, and never claim a clean audit the checks did not actually confirm.
Steps
- Select the change. If not given, run
openspec list --json, show active (non-archived) changes with schema, and let the user choose. Never guess. - Gather artifacts and convention docs. Run
openspec status --change "<name>" --jsonandopenspec instructions apply --change "<name>" --json; collect every artifact path fromcontextFilesplus.openspec.yaml. If the CLI is unavailable, fall back to filesystem discovery underopenspec/changes/<name>/. Locate repo-root convention docs (AGENTS.md,CLAUDE.md,CONTRIBUTING.md) and the schema'scontext/rulesif available from/rhdh-spec-driven-schema. - Enforce the apply-ready minimum before doing anything else. Build the
union of the schema's
apply.requires(or CLIapplyRequires) and{proposal, design, specs, tasks}. Preferred: every ID in that union must showstatus: "done"in the status JSON. Filesystem fallback: read.openspec.yamlfor the schema name, read that schema'sapply.requires, and check each mapped path exists and is non-empty (proposal->proposal.md,design->design.md,tasks->tasks.md,specs->at least onespecs/**/spec.md). If the required set cannot be determined, or any required artifact is missing/not done: report CRITICAL, state "Audit blocked (CRITICAL findings remain)", write/updateaudit.mdwith the current UTC timestamp, suggest/openspec-continue-change, and stop — do not build the ownership map or spawn the auditor. - Build a cross-change ownership map. Resolve sibling changes (reuse
openspec list --jsonfrom step 1, or filesystem-listopenspec/changes/*excluding this change andarchive/). For each sibling, read only itsproposal.mdCanonical Touchpoints section anddesign.mdDecisions section, and build a lightweightcapability/namespace/claim -> [change names]map. Pass the map (or condensed claim lines), not full sibling trees, to the auditor. If sibling discovery fails entirely, pass an empty map and note category E ran degraded in the final report — do not fail the whole audit for this alone. - Spawn an independent auditor subagent (Task tool,
subagent_type: general-purpose). Give it only: change name, absolute artifact paths, the ownership map, convention doc paths, the checklist below, and the required JSON return schema. Explicitly forbid passing authoring rationale or "what we meant" — this is prompt isolation, not a sandbox; instruct it to limit reads to the given paths. Require it to return:
What ships with it
2 files 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.
- 7d ago First seen · 135 lines · 79 tokens per session scan A 1a4fe381fabe
openspec-audit-change is a skill published in the GitHub repository redhat-developer/rhdh-skills (16 stars, last pushed 3d ago), licensed Apache-2.0. It adds 79 tokens to every session and 2,003 once invoked, about $0.0004 per session on Opus 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 2026-08-30.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
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"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…