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/jmanhype/speckit/speckit.linear.syncgit clone --depth 1 https://github.com/jmanhype/speckitWhat 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 | $0.00014 | $0.01036 |
| Opus 5 | $0.00007 | $0.00518 |
| Sonnet 5 | $0.00003 | $0.00207 |
| Haiku 4.5 | $0.00001 | $0.00104 |
Grade A, and why
speckit.linear.sync 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 yesterday.
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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
User Input
$ARGUMENTS
You MUST consider the user input before proceeding (if not empty).
Outline
-
Validate prerequisites:
- Run
.specify/scripts/bash/check-prerequisites.sh --json --require-tasks --include-tasks - Parse FEATURE_DIR and verify tasks.md exists
- Load
.specify/linear-mapping.jsonfor task-to-issue mapping
- Run
-
Determine sync direction:
--to-linear: Push tasks.md status → Linear (default)--from-linear: Pull Linear status → tasks.md--bidirectional: Merge both (Linear wins on conflicts)
-
Fetch current state from both sources:
From tasks.md:
- Parse each task's completion status
[x]vs[ ] - Extract task IDs and descriptions
From Linear (using mapped issue IDs):
- Fetch each issue's current status
- Map Linear status to completion:
Linear Status tasks.md Done, Completed, Closed [x]In Progress [ ](with note)Todo, Backlog [ ]Canceled [-](skipped)
- Parse each task's completion status
-
Detect changes and conflicts:
Sync Analysis: | Task | tasks.md | Linear | Action | |------|----------|--------|--------| | T001 | [x] | In Progress | → Update Linear to Done | | T002 | [ ] | Done | ← Update tasks.md to [x] | | T003 | [x] | Done | ✓ In sync | | T004 | [ ] | Todo | ✓ In sync | -
Apply changes based on direction:
--to-linear (default):
- For each task marked
[x]in tasks.md:- Update Linear issue status to "Done"
- For tasks marked
[ ]:- If Linear shows "Done", warn about potential regression
--from-linear:
- For each Linear issue marked "Done":
- Update tasks.md to
[x]
- Update tasks.md to
- For issues "In Progress":
- Add comment to task:
<!-- In Progress in Linear -->
- Add comment to task:
--bidirectional:
- Linear status takes precedence on conflicts
- Update both systems to match
- For each task marked
-
Update tracking metadata:
- Update
.specify/linear-mapping.jsonwith sync timestamp:{ "last_sync": "2025-01-15T14:30:00Z", "sync_direction": "bidirectional", "changes_applied": 3 }
- Update
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.
- yesterday First seen · 136 lines · 14 tokens per session scan A 3f2aede72314
speckit.linear.sync is a command published in the GitHub repository jmanhype/speckit (26 stars, last pushed 5mo ago), licensed MIT. It adds 14 tokens to every session and 1,036 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 2026-09-01.
Other commands, from other repositories
paul:verify
Guide manual user acceptance testing of recently built features.
quick-fix
Fast-track workflow for small bug fixes.
sync-linear
Sync current work with Linear ticket status.
review
Review the current diff for violations of the conventions in AGENTS.md and .cursor/rules/. Report findings ordered by severity; do not fix anything unless asked.
flow-refine
Run the canonical flow/refine Flow lifecycle.
flow-revert
Run the canonical flow/revert Flow lifecycle.