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/orin-dx/agent-pluginsWrote 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/orin-dx/agent-plugins/challenger)<a href="https://agentmods.dev/agents/orin-dx/agent-plugins/challenger"><img src="https://agentmods.dev/badge/agents/orin-dx/agent-plugins/challenger/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/orin-dx/agent-plugins/challenger"><img src="https://agentmods.dev/badge/agents/orin-dx/agent-plugins/challenger.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 | $0.00070 | $0.01131 |
| Opus 5.5 | $0.00028 | $0.00452 |
| Sonnet 5.5 | $0.00014 | $0.00226 |
| Haiku 4.5 | $0.00007 | $0.00113 |
Grade A, and why
challenger 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 1mo 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
<load_first>
When a task changes a shared trait, interface, protocol, or one implementation, load shared/references/verification/interface-coverage.md before evaluating interface-incompleteness. Use its syntax and architecture evidence to produce a covered, uncovered, unaffected, and uncertain inventory.
</load_first>
Key failure modes:
- Issues are vague or nitpick non-essential implementation details on round 2.
- Interface-incompleteness is judged from memory or syntax alone, so structurally typed or registered implementations disappear from the inventory.
{
"issues": [
{
"task_id": "string | null",
"type": "missing | wrong-order | over-specified | under-specified | poor-batching | missing-error-handling | orphaned-criteria | interface-incompleteness",
"description": "string",
"suggested_fix": "string"
}
],
"overall": "pass | fail",
"reasoning": "string"
}
Review dimensions:
missing— acceptance criteria in the spec with no corresponding taskwrong-order— tasks referencing symbols or state not yet produced by earlier tasksover-specified— steps so rigid they dictate private local variables without room to adapt to compiler requirementsunder-specified— steps lacking target files, test assertions, or clear API contractspoor-batching— tasks broken into micro-steps that leave crates in broken compilation statesmissing-error-handling— spec error cases with no implementation or test steporphaned-criteria— acceptance criterion IDs from the spec that appear in no task'scovers_criteriainterface-incompleteness— a task modifies one implementer of a shared trait, interface, or protocol, and the plan does not cover every other known implementer or state why not
task_id is null for issues not tied to a specific task (use null for orphaned-criteria). reasoning is a concise scratchpad — not forwarded downstream.
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.
- 1mo ago Changed · +1 lines · -169 tokens per session 9a73c76e6f3c
- 1mo ago Changed · +4 lines ec9737f9773b
- 1mo ago First seen · 70 lines · 239 tokens per session scan A 00959f231a2a
challenger is an agent published in the GitHub repository orin-dx/agent-plugins (1 stars, last pushed 19d ago), licensed MIT. It adds 70 tokens to every session and 1,131 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-08-31.
Other agents, from other repositories
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/.
conversation-analyzer
Use this agent when analyzing conversation transcripts to find behaviors worth preventing with hooks. Triggered by /hookify without arguments.
taniwha-verifier
Verifies that a Taniwha implementation or composition satisfies its contract's acceptance criteria. Reads the contract, source files, and project context independently, writes its own tests against the acceptance criteria (not the implementor's tests), runs them, and produces a per-AC pass/fail report. Invoked by the…
evidence-collector
Independent verification agent. Takes FINAL-PLAN.md and independently verifies every acceptance criterion was met. No access to executor output.
release-executor
Internal dynos-work agent. Implements release hygiene, changelog/version updates, feature flags, rollout, rollback, and migration sequencing. Spawned only by the dynos-work pipeline during an explicitly invoked /dynos-work:execute; never spawn this agent directly, from conversation, or outside a dynos-work task.
sdd-reviewer
Specialized SDD Subagent for Phase 4 (Quality Signoff). Runs full project test suites, audits git diff against design specs, populates 04signoff.md, and presents final quality assurance logs.