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/nodnarbnitram/claude-code-extensions/existing-lineargit clone --depth 1 https://github.com/nodnarbnitram/claude-code-extensionsWhat 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 | $0.00013 | $0.01046 |
| Opus 5 | $0.00006 | $0.00523 |
| Sonnet 5 | $0.00003 | $0.00209 |
| Haiku 4.5 | $0.00001 | $0.00105 |
Grade A, and why
existing-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 — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Existing Linear PR Workflow
Create a new PR for an existing Linear ticket when additional related code changes are required.
Activate the linear skill first and use its wrapper scripts for all Linear operations. Do not call another Linear CLI directly from this workflow.
Context
- Current git status: !
git status --short - Current branch: !
git branch --show-current - Staged changes: !
git diff --cached --stat - Unstaged changes: !
git diff --stat
Arguments
$1- Linear ticket identifier (e.g.,ICE-2004)--skip-validation- Optional flag in$ARGUMENTSto skip success criteria validation
If ticket ID is missing, ask the user for it.
Prerequisites
- Changes should already be made to files (staged or unstaged)
- The
linearskill must be available and its wrapper scripts must run successfully ghCLI must be authenticated
Steps
Track these steps as TODOs and complete them one by one.
-
Parse arguments - Extract ticket ID (
$1) and check for--skip-validationin$ARGUMENTS. -
Read Linear ticket - Fetch ticket details with the
linearskill wrapper:uv run .claude/skills/linear/scripts/read-ticket.py $1- Extract:
identifier,title,description,branchName,state,url - If ticket not found, stop and inform the user.
- Extract:
-
Validate success criteria (skip if
--skip-validationis present)- Present the ticket details:
## Ticket: <identifier> **Title:** <title> **Status:** <state.name> **Description:** <description> - Ask: "Does this match the work you're committing? (yes/no)"
- If no, ask for clarification and document for PR description.
- Present the ticket details:
-
Review changes - Analyze the context above.
- If no changes exist, stop and inform the user.
- Summarize what will be committed.
-
Create or checkout branch - Use the Linear branch name:
git checkout -b <branchName>- If branch exists locally:
git checkout <branchName> - If already on correct branch, continue.
- If branch exists locally:
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 · 133 lines · 13 tokens per session scan A a83fb75b4244
existing-linear is a command published in the GitHub repository nodnarbnitram/claude-code-extensions (16 stars, last pushed 4mo ago), licensed MIT. It adds 13 tokens to every session and 1,046 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 2026-08-30.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.