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/microsoft/sre-agent/pr-deliverynpx skills add microsoft/sre-agent --skill pr-deliverygit clone --depth 1 https://github.com/microsoft/sre-agentWhat 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 | $0.00083 | $0.00829 |
| Opus 5 | $0.00042 | $0.00415 |
| Sonnet 5 | $0.00017 | $0.00166 |
| Haiku 4.5 | $0.00008 | $0.00083 |
Grade A, and why
pr-delivery 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 3d 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Zava Learning — Pull Request Delivery (IaC + Code)
Single owner of GitHub pull-request creation for durable fixes. Repo: @@REPO@@
(hosts the app src/ and the infrastructure infra/). This skill applies once an incident is
root-caused and the live mitigation is in place; the pull request it produces is later referenced
by the ServiceNow Change Request (servicenow-change-management).
There is no native GitHub pull-request tool — author the branch, commit, and open the PR with
ExecutePythonCode (GitHub REST API / gh) using FindConnectedGitHubRepo and
GetIaCForGitHub to locate the repo and IaC. Never commit secrets. Before opening the PR, retrieve
SearchMemory("zava-redaction") and run its redact() over the PR title, body, and commit message
(and never stage a credential or .env/*.pem/git-credentials file into the diff).
When to use
- An incident is root-caused to a durable defect and the live mitigation is already applied.
- The fix belongs in version control: IaC (
infra/, e.g. an NSG rule ininfra/modules/network.bicep, or a value ininfra/main.parameters.json) or application code (src/, e.g. a synchronous crypto regression insrc/assessment-api/server.js).
Decide the change class
- Infrastructure (IaC): the fix is a guardrail or config in Bicep / parameters. Make BOTH live Azure and the committed IaC reflect the corrected state so the next deploy keeps the fix.
- Application code: the fix is in
src/. The live mitigation was a revision rollback/restart; the PR carries the actual code correction.
Steps
- Resolve the repo and IaC type (
FindConnectedGitHubRepo,GetIaCForGitHub). - Branch from default:
fix/<symptom-slug>(e.g.fix/quiz-launch-nsg-priority). - Apply the minimal, surgical change. Match existing style. Touch only what the root cause requires.
- Commit with a conventional message:
fix(<area>): <symptom> — <root cause>and a body that summarizes the RCA and links the PagerDuty incident. - Open the PR against
@@REPO@@. PR body must include: symptom, root cause, the change, verification evidence (link the Before/After), and the PagerDuty incident number. - Capture the PR URL — the ServiceNow Change Request (
servicenow-change-management) references it. Post the PR link back in the PagerDuty incident notes.
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.
- 3d ago First seen · 61 lines · 83 tokens per session scan A c97280dbba6a
pr-delivery is a skill published in the GitHub repository microsoft/sre-agent (149 stars, last pushed 9d ago), licensed MIT. It adds 83 tokens to every session and 829 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
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…