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/suyoumo/clawprobench/linearnpx skills add suyoumo/ClawProBench --skill lineargit clone --depth 1 https://github.com/suyoumo/ClawProBenchWhat 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 | $0.00045 | $0.01755 |
| Opus 5 | $0.00023 | $0.00877 |
| Sonnet 5 | $0.00009 | $0.00351 |
| Haiku 4.5 | $0.00005 | $0.00176 |
Grade A, and why
linear 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 — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Linear API Skill
You have access to the Linear GraphQL API via the http tool. Credentials are automatically injected — never construct Authorization headers manually. When the URL host is api.linear.app, the system injects Authorization: {linear_api_key} transparently (no Bearer prefix — Linear API keys are sent raw).
Identity bootstrap (first use)
Linear's API key does not tell you who the user IS inside Linear. Before running any "my issues" / "assigned to me" / "my tickets" request, make sure the user's Linear identity is cached. This avoids re-fetching viewer on every request and makes filter-by-assignee queries deterministic.
Cache file
Path: context/intel/linear-identity.md
Shape:
---
type: linear-identity
bootstrapped_at: 2026-04-21
refreshed_at: 2026-04-21
stale_after: 2026-05-21
---
# Linear identity
user_id: 8a7f...-uuid
display_name: Tobias Holenstein
email: tobias@...
timezone: Europe/Zurich
## Teams
- id: team-uuid-a, key: ENG, name: Engineering
- id: team-uuid-b, key: PROD, name: Product
## Default team
ENG
Bootstrap flow
memory_read("context/intel/linear-identity.md"). If the file exists andstale_afteris in the future, use it and stop.- If missing or stale, run one GraphQL call:
query { viewer { id name displayName email } teams(first: 50) { nodes { id key name } } } - Write the cache via
memory_writewithstale_after= today + 30 days. - If the returned team list has exactly one team, record it as
Default team. If more than one, ask the user once: "I see teams ENG, PROD, OPS. Which one do you default to for new issues?" and store the answer. - On HTTP 401 or an
AuthenticationErrorGraphQL error, invalidate the cache and re-prompt the user to check their API key — do not silently retry.
Using the cached identity
- "list my issues" / "what's assigned to me" → filter by
assignee: { id: { eq: "<cached user_id>" } }, not byassignee: { isMe: true }(theisMefilter is not universally available andviewerround-trips are wasteful). - "create an issue in my team" → use cached
Default teamid without asking. - "create an issue in " → match against cached team names; ask only if no match.
- Skills that import external work into Linear must consume this cache rather than re-resolving identity per run.
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 · 160 lines · 45 tokens per session scan A 708eb495dbf8
linear is a skill published in the GitHub repository suyoumo/ClawProBench (823 stars, last pushed 8d ago), licensed Apache-2.0. It adds 45 tokens to every session and 1,755 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
lastlight-evals
Scaffold, configure and run a Last Light EVALS workspace — the harness that runs Last Light's real workflows against a mocked GitHub and grades them deterministically. Use when the user wants to "set up / scaffold Last Light Evals", "create an evals workspace or instance", "run evals", "compare models", or author new…
issue-comment
Handle a non-build maintainer comment on an issue or PR — close, reopen, label, dedupe, answer a brief question, or triage. Action-only; redirect anything that needs code changes to /build.
chat
Conversational assistant for messaging-platform threads (Slack, Discord). Answer questions about repos, PRs, and issues, explain code, and guide users to the natural-language workflow triggers listed in the system prompt.
Evaluation
Frames model, prompt, and system evaluation as a reproducible experiment with baselines, datasets, and explicit metrics.
perpetuum
为一个或多个项目建立、运行和管理长期 Agent 队伍。适用于初始化长期自主工作、按项目 cron 计划持续推进 Story、查看或调整 Story 看板,以及处理人类输入。.
openspec-archive-change
Archive a completed change in the experimental workflow. Use when the user wants to finalize and archive a change after implementation is complete.