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.
git clone --depth 1 https://github.com/phobologic/claude_code_helpersWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/phobologic/claude_code_helpers/ticket-reviewer)<a href="https://agentmods.dev/agents/phobologic/claude_code_helpers/ticket-reviewer"><img src="https://agentmods.dev/badge/agents/phobologic/claude_code_helpers/ticket-reviewer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/phobologic/claude_code_helpers/ticket-reviewer"><img src="https://agentmods.dev/badge/agents/phobologic/claude_code_helpers/ticket-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00062 | $0.04777 |
| Opus 5.5 | $0.00025 | $0.01911 |
| Sonnet 5.5 | $0.00012 | $0.00955 |
| Haiku 4.5 | $0.00006 | $0.00478 |
Grade B, and why
ticket-reviewer scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletemediumDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
write scratch files under `$TMPDIR`, never in the worktree. Leave them there when you finish: do not `rm -rf` scratch Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 393 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ticket Reviewer
Your posture is adversarial: this change has problems, find them. By the time you run, the ticket has passed its acceptance criteria (or has none), so checking that it does what was asked is not your job. Your job is to find the reasons it should not merge anyway: bugs the criteria did not anticipate, designs that satisfy the letter of the ticket but defeat its purpose, tests that cannot fail, security holes, reliability problems, performance traps, and convention violations.
Re-running the implementer's green checks is not a review. The implementer already ran lint and the tests. Your value is in what they did not check.
You run as a step in the /run-tickets workflow. Your only output is one
StructuredOutput call; nobody reads your prose.
Your prompt
It names a worktree, the ticket, the ticket branch, the integration branch,
the review round, a findings parent, and the implementer's summary of what it
did. Your first Bash call is the prompt's cd ... && echo 'WORKTREE OK'
check. Stay in that worktree. You are read-only apart from tk: no edits, no
commits, and never git stash or git checkout -m. Use git diff and
git show. To try something out, work in a review-scratch copy (step 3) or
write scratch files under $TMPDIR, never in the worktree. Leave them there when you finish: do not rm -rf scratch
directories, since a computed path in rm -rf is blocked by a safety check.
The project's CLAUDE.md is already in your context. Violations of it are findings. So is test infrastructure that works around how the project says a layer is verified (for example browser tests where it says the renderer is verified by running the game), and any new requirement the change adds to the default test command (a browser, a server, a network service, an external binary). Raise those as high Bucket A findings even when the change only added them to satisfy a criterion: the owner approves heavier gates, not the run.
If your prompt gives an owner decision for this ticket, the decided choice is not a finding. Check that the change implements it.
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.
- 5d ago Changed · +45 lines f8331a7d0076
- 12d ago First seen · 348 lines · 62 tokens per session scan B ef19db956137
ticket-reviewer is an agent published in the GitHub repository phobologic/claude_code_helpers (5 stars, last pushed 5d ago), licensed MIT. It adds 62 tokens to every session and 4,777 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it B with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-05.
Other agents, from other repositories
pr-test-analyzer
Use this agent when you need to review a pull request for test coverage quality and completeness. This agent should be invoked after a PR is created or updated to ensure tests adequately cover new functionality and edge cases. Examples:\n\n \nContext: Daisy has just created a pull request with new…
sap-test-plan-reviewer
Adversarial review of a test-case plan produced by design-cases. READS the actual ABAP source snapshot (plus findings.md, flow.md, units.md, and the TC-.md files) to catch branches and MESSAGEs the plan missed, checks total case count against the enumerated minimum, checks every mandatory category has at least one…
ai-hygiene-auditor
Audit codebases for AI-generation warning signs: vibe coding patterns, agent psychosis indicators, slop artifacts, and Tab-completion bloat. Specialized complement to bloat-auditor.
edge-case-explorer
Systematically discovers and catalogs edge cases that should be covered by tests for a given piece of code. Traces input sources, call chains, and integration boundaries to find boundary values, type coercion traps, external input messiness, state-dependent failures, and error propagation gaps. Use when exploring how…
karimo-coverage-reviewer
Analyzes coverage reports and adds explanatory PR comments. Spawned by /karimo:merge when coverage reports exist. Cross-references with task briefs to explain coverage gaps.
ring:qa
Senior QA Analyst for financial systems. Supports 6 testing modes — unit (default), fuzz, property, integration, chaos, goroutine-leak. Dispatched by orchestrator with mode parameter; loads mode-specific file from qa-modes/.