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/eigenwise/eigenwise-toolshed/sidequestnpx skills add Eigenwise/eigenwise-toolshed --skill sidequestgit clone --depth 1 https://github.com/Eigenwise/eigenwise-toolshedWhat 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 | $0.00049 | $0.04302 |
| Opus 5 | $0.00024 | $0.02151 |
| Sonnet 5 | $0.00010 | $0.00860 |
| Haiku 4.5 | $0.00005 | $0.00430 |
Grade A, and why
sidequest 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 — 258 lines — stays where its author put it; the contents beside it link to each section on GitHub.
sidequest
A Trello-light quest log: tickets in a central store under ~/.claude/sidequest, a live
Kanban dashboard, one CLI (bin/sidequest.js), matching MCP tools. Detail lives in reference files
— read them only when the situation calls for it:
references/orchestration.md— decomposition depth, fan-out waves, checkpoints, background execution, cost levers, agent teams.references/experiment-loop.md— oracle rounds, branches, verdicts, promotion.references/publishing.md— delivery modes, publish transaction.references/routing-details.md,references/routing-guide.md— routes and wiring.references/high-stakes.mdreferences/external-trackers.md,references/board-features.md,references/category-links.md,references/ticket-authoring.md,references/invocation-contracts.md.
Plan substantial work on the board first
Before dispatching substantial or ambiguous work, pin a contract; see user-story.
For substantial work:
- solo-fit gate. SOLO-FIT picks one-executor vs wave; it NEVER means you implement inline. Small coherent work gets one ticket and one executor; use it too when the contract cannot be pinned without doing the work. With a written spec and executable done-oracle, contract-first wave is the default. Claiming the contract is unpinnable needs either a completed exploration/planning ticket that tried and names the interface that resisted a written contract, or no written contract surface in the request. “Feels coupled” is not evidence: when unsure, file planning first.
- Ticket shape. If a written spec pins shared types/interfaces, file boundaries, and
per-piece verification, 3+ independently checkable pieces use contract-first fan-out: pin the
contract in ticket descriptions or a short planning ticket, then one parallel wave on
category-appropriate cheaper models and integrate once per wave. Wave mode REQUIRES a Sidequest story first
(
sidequest story add, then--story US-nper piece): file the complete backlog under it and pin the execution contract on it. A story is Sidequest's ownUS-ngrouping, not a Claude Code feature. One-ticket mode stays story-less; use stories for shared outcomes or dependencies. Cut along affected surfaces: store, CLI, MCP surface, skill/docs, and applicable full test directory. Tickets carry anchors, contract, and a scoped verify. Use directory scope for the blast radius; details:references/ticket-authoring.md. - Link dependencies (
link SQ-4 depends-on SQ-3); shape a story as design → wave(s) → integrate soreadyserializes the phases. - File the whole planned wave backlog before dispatching. Give every ticket scope, dependencies, and per-ticket verification; dispatch each ready wave concurrently. Do not drip-file a serial chain.
What ships with it
12 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.
- references/board-features.md 3.7 KB
- references/category-links.md 3.0 KB
- references/experiment-loop.md 2.7 KB
- references/external-trackers.md 1.8 KB
- references/high-stakes.md 839 B
- references/invocation-contracts.md 4.7 KB
- references/orchestration.md 47 KB
- references/orchestrator-checkpointing.md 2.4 KB
- references/publishing.md 16 KB
- references/routing-details.md 7.4 KB
- references/routing-guide.md 5.8 KB
- references/ticket-authoring.md 5.4 KB
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 · 258 lines · 49 tokens per session scan A 5a98b9c72b23
sidequest is a skill published in the GitHub repository Eigenwise/eigenwise-toolshed (36 stars, last pushed 5d ago), licensed MIT. It adds 49 tokens to every session and 4,302 once invoked, about $0.0002 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…