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/redhat-developer/rhdh-skills/mutation-gatenpx skills add redhat-developer/rhdh-skills --skill mutation-gategit 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/mutation-gate)<a href="https://agentmods.dev/skills/redhat-developer/rhdh-skills/mutation-gate"><img src="https://agentmods.dev/badge/skills/redhat-developer/rhdh-skills/mutation-gate.svg" alt="Measured on agentmods" 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 | $0.00105 | $0.01092 |
| Opus 5 | $0.00053 | $0.00546 |
| Sonnet 5 | $0.00021 | $0.00218 |
| Haiku 4.5 | $0.00011 | $0.00109 |
Grade A, and why
mutation-gate 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 4d 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RHDH write gate
An external write is anything the user cannot undo by closing the session: a pushed commit, an opened pull request, a Jira transition, a posted message, a file changed in someone else's repository.
Reading is not a write. A request to fetch, triage, analyse, or report is intent to read, and it approves nothing.
The gate
1. State the operations. List every operation you are about to perform, in the order you will perform them. For each one give:
| Field | What it carries |
|---|---|
| Target | The exact thing being changed: owner/repo#412, RHIDP-1234, a branch name, a channel |
| Command | The exact command or request, as it will run. Not a paraphrase |
| Preview | The body, label, field value, or diff that will land |
| Precondition | What must already be true. Check it immediately before executing, and stop the batch if it is not |
| On failure | What happens to the operations after this one if it fails |
| Recovery | How to undo or contain this operation once it has happened |
Render this as a table in the conversation. Approval happens where the user already is, so the plan goes to them rather than to a file.
Recovery is not optional, and it is not the same as failure handling. Failure handling says what happens to the operations that have not run yet. Recovery says what to do about the one that already did. Write it before asking for approval: an operation you cannot say how to undo is one the user is approving blind. Where there is genuinely no undo — a posted message, a triggered pipeline, a published package — say that, in those words. "Cannot be undone; the message stays" is a complete and useful recovery entry. Silence is not.
When a plan is too large to read in the transcript — a multi-repository bump, a
catalog change touching dozens of files — write it to a file in the operating
system temporary directory instead, following /handoff's convention, and print
the absolute path. Do not write it into the user's checkout, where it can reach a
commit.
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.
- 4d ago First seen · 99 lines · 105 tokens per session scan A 10f9c3de6393
mutation-gate is a skill published in the GitHub repository redhat-developer/rhdh-skills (16 stars, last pushed today), licensed Apache-2.0. It adds 105 tokens to every session and 1,092 once invoked, about $0.0005 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…