Borrowing it
Nothing to install: this file belongs to atheurer/agentic-perf. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/atheurer/agentic-perf/main/.agents/skills/agentic-perf-orchestration/SKILL.mdgit clone --depth 1 https://github.com/atheurer/agentic-perfWrote 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/atheurer/agentic-perf/agentic-perf-orchestration)<a href="https://agentmods.dev/skills/atheurer/agentic-perf/agentic-perf-orchestration"><img src="https://agentmods.dev/badge/skills/atheurer/agentic-perf/agentic-perf-orchestration/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/atheurer/agentic-perf/agentic-perf-orchestration"><img src="https://agentmods.dev/badge/skills/atheurer/agentic-perf/agentic-perf-orchestration.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 | $0.00036 | $0.00983 |
| Opus 5.5 | $0.00014 | $0.00393 |
| Sonnet 5.5 | $0.00007 | $0.00197 |
| Haiku 4.5 | $0.00004 | $0.00098 |
Grade A, and why
agentic-perf-orchestration 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 today.
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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agentic-perf orchestration development
Use this skill when changing prompt assembly, agent context, handoffs, dispatch, ticket state, cancellation, or iterative benchmark behavior. Follow the repository's AGENTS.md for general development standards and docs/reviewing.md for project review checks. Use the PR-cycle skill for review and landing of the resulting pull request.
Context and handoffs
- Preserve user-authored and agent-specific directives verbatim when the contract requires it.
- Keep supplemental context additive. Avoid repeating directives or parsed specifications that are already present.
- Filter system and agent handoff chatter from an agent's initial task context unless it contains a user-relevant decision.
- Keep supported context keys, schemas, and agent capabilities in one source of truth where practical; derive secondary lists from it.
- When changing a message contract, trace every producer, consumer, prompt, schema, and test.
Discovery and state transitions
- Enumerate the complete resource set before selecting a host, NIC, role, or capability. If a required resource cannot be verified, report the gap or ask for clarification instead of guessing from a partial inventory.
- Distinguish “not found,” “not checked,” and “not supported” in status and error messages.
- Verify the running service version when stale processes could explain the observed behavior.
- Treat cancellation, approval pauses, retries, and restart boundaries as state-machine behavior. Test the normal, partial, repeated, and failure paths.
Develop in an isolated instance
-
Search for an existing GitHub issue covering the work. If none exists, create a focused issue before implementation and include clear acceptance criteria.
-
From the selected repository root, prepare a managed instance based on the intended base (normally
origin/main):./scripts/dev-instance.sh prepare --issue NUMBER --base origin/main
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.
- today First seen · 93 lines · 36 tokens per session scan A d38c98e7e17a
agentic-perf-orchestration is a skill published in the GitHub repository atheurer/agentic-perf (6 stars, last pushed today), licensed Apache-2.0. It adds 36 tokens to every session and 983 once invoked, about $0.0001 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 2026-10-29.
Other skills, from other repositories
sync-bridge
Reviews and guides Chromium Sync Model API (DataTypeSyncBridge) implementations, including DataTypeStore persistence and forwards/backwards compatibility for sync specifics. Use when implementing or reviewing a DataTypeSyncBridge subclass, DataTypeStore usage, sync metadata persistence, conflict resolution, or…
sync-model-processor
Reviews changes to Chromium Sync model internals in components/sync/model/, including ClientTagBasedDataTypeProcessor, ClientTagBasedRemoteUpdateHandler, ProcessorEntity, ProcessorEntityMetadata, and ProcessorEntityTracker. Use when modifying or reviewing processor state transitions, entity metadata tracking, conflict…
adversarial-reviewer
Stress-test a code change for concrete correctness defects, unsafe assumptions, and failure modes. Use when the user explicitly asks for an adversarial review, a deep bug hunt, or to tear a change apart, or to check your own change before submitting it. Do not use for ordinary review, style feedback, or general…
gsd-ns-review
Invoke this Pi skill with /skill:gsd-ns-review.
gitnexus
A code-graph analysis add-on for examining an existing codebase, including symbols, call paths, execution flows, and effects across repositories. It can query GitNexus through its command-line or MCP interfaces.
issue
Use when starting a chain from a GitHub issue — turning an issue URL or number into a triaged, planned, dispatched, and reviewed pull request. Classifies the thread (bug → root-cause discipline, feature → plan chain, question → drafted reply), synthesizes a spec from the issue's own acceptance criteria, then runs the…