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 commands/ruslan-korneev/claude-plugins/cyclegit clone --depth 1 https://github.com/ruslan-korneev/claude-pluginsWhat 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 | $0.00011 | $0.00875 |
| Opus 5 | $0.00005 | $0.00438 |
| Sonnet 5 | $0.00002 | $0.00175 |
| Haiku 4.5 | $0.00001 | $0.00088 |
Grade A, and why
linear:cycle 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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Command /linear:cycle
Manage Linear cycles (sprints).
Instructions
Step 0: Validate Configuration
Check LINEAR_API_KEY and LINEAR_TEAM are set.
Step 1: Resolve Team ID
Use teams query to resolve $LINEAR_TEAM to UUID.
Step 2: Execute Action
action=current (default)
Fetch cycles, find the active one (where startsAt <= today <= endsAt and completedAt is null). Fetch its issues.
Display:
## Current Cycle: Sprint 42
**Period**: Mar 4 — Mar 18, 2026
**Progress**: 12/20 issues completed
[████████████░░░░░░░░] 60%
### Breakdown by Status
| Status | Count | Points |
|--------|-------|--------|
| Done | 8 | 21 |
| In Review | 1 | 3 |
| In Progress | 4 | 13 |
| Todo | 2 | 3 |
| Backlog | 3 | 5 |
| **Total** | **18** | **45** |
### Remaining Work
| ID | Title | Status | Assignee | Pts |
|----|-------|--------|----------|-----|
| TEAM-123 | Auth flow | In Progress | John | 5 |
| TEAM-124 | Pagination | In Progress | Jane | 3 |
| ... |
action=list
Fetch all cycles for team. Display:
## Cycles
| # | Name | Period | Issues | Completed | Progress |
|---|------|--------|--------|-----------|----------|
| 42 | Sprint 42 | Mar 4-18 | 20 | 12 | 60% |
| 41 | Sprint 41 | Feb 18-Mar 3 | 18 | 17 | 94% |
| 40 | Sprint 40 | Feb 4-17 | 15 | 15 | 100% |
Mark current cycle with an indicator.
action=stats
Fetch last 5 completed cycles. Calculate:
- Velocity: average completed points per cycle
- Throughput: average completed issues per cycle
- Completion rate: average % of scope completed
Display:
## Cycle Statistics
### Velocity (last 5 cycles)
| Cycle | Points Completed | Issues Completed | Completion |
|-------|------------------|------------------|------------|
| Sprint 41 | 34 | 17 | 94% |
| Sprint 40 | 30 | 15 | 100% |
| Sprint 39 | 28 | 14 | 88% |
| Sprint 38 | 32 | 16 | 94% |
| Sprint 37 | 26 | 13 | 81% |
**Average velocity**: 30 points/cycle
**Average throughput**: 15 issues/cycle
**Average completion**: 91%
### By Assignee (current cycle)
| Assignee | Completed | In Progress | Points |
|----------|-----------|-------------|--------|
| John Doe | 5 | 2 | 18 |
| Jane Smith | 4 | 1 | 12 |
| Bob Wilson | 3 | 1 | 10 |
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 · 129 lines · 11 tokens per session scan A 7c47d592ee75
linear:cycle is a command published in the GitHub repository ruslan-korneev/claude-plugins (4 stars, last pushed 6mo ago), licensed MIT. It adds 11 tokens to every session and 875 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 2026-08-31.
Other commands, from other repositories
promote-discussions
Check GitHub Discussions for highly voted learnings and promote them to Issues.
contact-upsert
Create or update a contact, optionally assign to groups.
sync
Sync the audit manifest with Azure DevOps work items — set the connector up for the first time (connect: verify the transport, report which auth path is in effect, prove access read-only, detect the board's process), push manifest bugs/tasks/phases to ADO (board states, sprint stamp, Remaining Work, comments), pull…
task
Add a tracked task to the audit manifest — every answer is a flag, and the dialogue only covers what the caller did not pass — move one between phases, or cancel work that will not be done. add allocates the id, initializes all orchestrator fields, updates fileIndex, and revalidates; move renumbers a task into another…
run
Audit pipeline: execute exactly one task by id, with status guards (done/blocked/inprogress) and blocker checks. --dry-run previews without mutating.
phase
Audit pipeline: everything a phase has done to it — add one to a plan that already exists, run it end to end (every ready task, parallel where safe, then sign-off), pin which phase the pipeline reaches for first, or cancel one that will not be done. A bare runs it; --dry-run previews the run without mutating.