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/cairn-framework/cairn/cairn-loop-scopenpx skills add cairn-framework/cairn --skill cairn-loop-scopegit clone --depth 1 https://github.com/cairn-framework/cairnWhat 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 | $0.00063 | $0.00901 |
| Opus 5 | $0.00032 | $0.00451 |
| Sonnet 5 | $0.00013 | $0.00180 |
| Haiku 4.5 | $0.00006 | $0.00090 |
Grade A, and why
cairn-loop-scope 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scope one loop unit
Loaded by cairn-dev loop mode at its Scope step. Inputs: the selected unit
(slug or finding code), its resolved node, its validated todo body when it has
one, and the bound $CAIRN.
Declared exits, exactly one, as the last line you return to loop mode:
SCOPED: a success criterion is written and implementation may begin.REROUTED: a prerequisite must land first; the tracker edits you made ARE this iteration, and loop mode goes straight to Land.LOOP HALTED: the unit cannot be scoped without a maintainer.
1. Orient
$CAIRN neighbourhood <node> --include-todos --include-changes
$CAIRN rationale <node>
$CAIRN deps <node> --direction in --transitive
Read all three before deciding anything. The first shows what already claims this area, including an active change you must not collide with. The second is the accepted authority over the node. The third is the blast radius.
If the unit has a todo body, its Scope, Depends on, and Acceptance sections bind here. Where the body and your orientation disagree, the body is the contract and the disagreement is worth reporting in the summary.
2. Respect accepted decisions
An accepted decision covering the node constrains the implementation. You may not contradict one inside this iteration. If the unit cannot be done without contradicting an accepted decision, that is not a coding problem:
- If the superseding decision is knowable, the gap IS the unit. Investigate,
stress-test two to four options, persist a justified recommendation as a
meta/artefact, create a blocked tracker item, and returnREROUTEDso the package lands. - If it needs a ruling only the maintainer can give, do the same and say so
plainly in the artefact. Never self-ratify a binding decision. A local-tier
decision may be accepted only through the receipt protocol: two independent lens
receipts bound to the subject hash and a
ratified_by: machinemarker when the loop signs (todo.decision-ratification-tiers).
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 · 86 lines · 63 tokens per session scan A 621e9a0abbe5
cairn-loop-scope is a skill published in the GitHub repository cairn-framework/cairn (40 stars, last pushed 3d ago), licensed Apache-2.0. It adds 63 tokens to every session and 901 once invoked, about $0.0003 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…