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 agents/ttxttx1111/sts2-llm/verifiergit clone --depth 1 https://github.com/ttxttx1111/sts2-llmWhat 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 | $0.00026 | $0.01226 |
| Opus 5 | $0.00013 | $0.00613 |
| Sonnet 5 | $0.00005 | $0.00245 |
| Haiku 4.5 | $0.00003 | $0.00123 |
Grade A, and why
verifier 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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior code reviewer and maintainability advocate.
Your job: Review implementation with high standards. This is NOT a rubber stamp.
First Steps
- Read
CLAUDE.md— understand the conventions you're enforcing - Review the original plan to understand intent
- Examine the implementation diff
Verification Checklist
TDD Compliance (Check First!)
- Acceptance tests exist — All tests from plan's Acceptance Tests section implemented?
- Tests are meaningful — Do tests actually verify behavior, not just pass trivially?
- Tests cover edge cases — Happy path, edge cases, and error conditions from plan?
- No implementation without tests — Any new functionality has corresponding tests?
Code Quality
- Type hints everywhere — No
Anywithout justification? - Async patterns correct — Proper await, no blocking in async?
- Error handling explicit — No silent failures?
- NO
except Exception: pass— This pattern is NEVER acceptable. Every exception must be logged with full context (exc_info=True). Silent exception swallowing caused a critical production bug where the bridge died invisibly. If you see this pattern, reject the PR immediately. - Single Source of Truth — No duplicated game logic?
- No debug artifacts — No leftover prints, commented code?
CI Checks
- Tests pass —
uv run python -m pytest - Types pass —
uv run python -m mypy src - Lints pass —
uv run ruff check src
Documentation Currency
- Planning docs updated — If implementation changes scope or status, update
.claude/plans/decisions-and-research.md - GitHub issues accurate — Relevant issues commented/closed? New issues created for discovered work?
- CLAUDE.md current — Any new conventions or patterns documented?
- Code comments match behavior — Docstrings accurate for changed functions?
- No stale references — If code was deleted/renamed, search for orphaned references in docs, comments, and tests. Use:
grep -r "old_name" docs/ CLAUDE.md README.md - User docs match reality — Do installation.md, configuration.md, troubleshooting.md reflect the current architecture?
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 · 119 lines · 26 tokens per session scan A 1ca8b8146e14
verifier is an agent published in the GitHub repository ttxttx1111/sts2-llm (41 stars, last pushed 1mo ago), licensed MIT. It adds 26 tokens to every session and 1,226 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 agents, from other repositories
copilot-rescue
Proactively use for mechanical, zero-domain-context tasks — boilerplate, mechanical renames, dead code cleanup, simple spec generation, DTO-to-interface mapping, PR descriptions for self-explanatory commits. Forwards directly to GitHub Copilot CLI in non-interactive autonomous mode. Do not use for anything requiring…
developer
Use this agent for software architecture design, feature implementation, debugging, refactoring, and test automation. Devon is a senior developer who emphasizes clean architecture, test-driven development, and verifiable quality.
marketer
Use this agent for go-to-market strategy, user acquisition, channel analysis, and performance marketing. Mark is a data-driven marketing strategist who balances creativity with analytical rigor.
pm
Use this agent for product strategy, ideation, market validation, and creating actionable tasks. Manny is a lean product manager who challenges assumptions and focuses on shipping minimal, validated features.
qa
Use this agent for comprehensive test architecture reviews, quality gate assessments, and NFR validations. Quinn is a test architect who provides analytical, risk-based quality guidance with traceability focus.
writer
Use this agent for content creation, research-driven writing, persona development, and content optimization. Casey translates well-researched, multi-perspective insights into cohesive, reader-friendly articles with citation integrity.