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/alleneubank/claude-code/greenlinegit clone --depth 1 https://github.com/alleneubank/claude-codeWhat 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 | $0.00044 | $0.00542 |
| Opus 5 | $0.00022 | $0.00271 |
| Sonnet 5 | $0.00009 | $0.00108 |
| Haiku 4.5 | $0.00004 | $0.00054 |
Grade A, and why
greenline 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.
What it actually says
Greenline
Bootstrap dev environment, then improve e2e test baseline through categorized fix iterations.
Arguments
$ARGUMENTS
- TEST_FILTER: grep/filter for test files or names (e.g.,
transfer,auth.spec.ts) - --skip-tilt: Skip Phase 1 (tilt already healthy)
- --no-commit: Skip committing fixes
Phase 1: Tilt Bootstrap (skip if --skip-tilt)
Follow the tiltup skill workflow. Exit when all resources reach runtime=ok, update=ok.
If a resource cannot be fixed after 3 iterations, report it and continue to Phase 2 — it may not block e2e tests.
Phase 2: E2E First Run
- Discover e2e config and the canonical test command
- Verify tilt environment is serving
- Locate spec files for bug verification
- Run suite (apply TEST_FILTER if provided), record pass/fail baseline
Phase 3: Categorize and Fix (Loop)
Follow the e2e skill taxonomy and fix rules. Fix in priority order: flaky, outdated, bug. Report unverified failures without fixing.
After each logical fix or batch (unless --no-commit):
- Run builds, checks, unit tests
- Commit per
git-best-practiceswith scope:fix(e2e): ...for test fixes,fix(scope): ...for bug fixes
Re-run suite after fixes. If failures changed, repeat categorization.
Exit: pass count improved from baseline AND no actionable failures remain.
Phase 4: Report
Combine tiltup and e2e skill report formats:
## Greenline Report
**Tilt**: <healthy|skipped|degraded>
**E2E**: X/Y passed (was A/B on first run)
### Fixed
- CATEGORY: `file:line` — what was fixed
### Remaining
- UNVERIFIED: `file:line` — needs spec or user decision
### Commits
- `hash` type(scope): description
Ralph Integration
For autonomous execution: /ralph /greenline [args]
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 · 66 lines · 0 tokens per session scan A 88db78e0369b
greenline is a command published in the GitHub repository alleneubank/claude-code (52 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 44 tokens to every session and 542 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 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.