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/g-research/bobbit/install-performance-optimisationnpx skills add G-Research/bobbit --skill install-performance-optimisationgit clone --depth 1 https://github.com/G-Research/bobbitWhat 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 | $0.00024 | $0.02072 |
| Opus 5 | $0.00012 | $0.01036 |
| Sonnet 5 | $0.00005 | $0.00414 |
| Haiku 4.5 | $0.00002 | $0.00207 |
Grade A, and why
install-performance-optimisation 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 2d 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Install Performance Optimisation
Install into the current Bobbit project only. Use gateway tools directly; never hand-roll HTTP requests. This procedure may create staff, but it must never update, delete, rename, replace, or silently recreate an existing staff record.
1. Preflight the current project
- Call
perf_programme_get_session_contextto read the gateway-issued current session ID, then callbobbit_read(operation: "get_session", sessionId: ...)for that exact session. Use only its returnedprojectId; do not infer project authority from connection information or the filesystem. - Call
bobbit_read(operation: "get_project", projectId: ...),bobbit_read(operation: "list_roles", projectId: ...), andbobbit_read(operation: "list_tools", projectId: ...)with bounded limits. Stop if the exact session or project is missing, the session does not carry a project ID, the pack is disabled, eitherperformance-scanner/optimisation-directoris unavailable, or the programme configuration tools are unavailable. - Call
perf_programme_get_settingsbefore changing anything. Retain any recorded Scanner and Director staff IDs for identity reconciliation.
2. Ask for operating settings
Use one ask_user_choices call containing all four questions. Each question has an Other escape hatch for a custom value.
- Scanner schedule:
Manual only (manual),Every 15 minutes (*/15 * * * *),Hourly (0 * * * *),Daily at 02:00 (0 2 * * *). - Director schedule:
Manual only (manual),Hourly (15 * * * *),Every 4 hours (15 */4 * * *),Daily at 03:00 (0 3 * * *). - Ideator parallelism:
2,4,6. - Active-goal target:
1,2,3,4.
Accept the exact sentinel manual (including a user's unambiguous “Manual only” answer) or validate a custom schedule as a standard five-field cron expression. Validate custom counts as positive bounded integers accepted by perf_programme_set_settings. Use the current project timezone when authoritative project configuration supplies one; otherwise explicitly use and report UTC. Do not silently repair invalid input: ask again with the validation error.
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.
- 2d ago First seen · 96 lines · 24 tokens per session scan A 91d4c8e04abf
install-performance-optimisation is a skill published in the GitHub repository G-Research/bobbit (11 stars, last pushed 2d ago), licensed MIT. It adds 24 tokens to every session and 2,072 once invoked, about $0.0001 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.
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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…