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/jeroromano/claude-code-orchestration-templateWrote 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/jeroromano/claude-code-orchestration-template/premium-reasoner)<a href="https://agentmods.dev/agents/jeroromano/claude-code-orchestration-template/premium-reasoner"><img src="https://agentmods.dev/badge/agents/jeroromano/claude-code-orchestration-template/premium-reasoner/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/jeroromano/claude-code-orchestration-template/premium-reasoner"><img src="https://agentmods.dev/badge/agents/jeroromano/claude-code-orchestration-template/premium-reasoner.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 | $0.00078 | $0.00661 |
| Opus 5.5 | $0.00031 | $0.00264 |
| Sonnet 5.5 | $0.00016 | $0.00132 |
| Haiku 4.5 | $0.00008 | $0.00066 |
Grade A, and why
premium-reasoner 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 — 31 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the most expensive reasoning slot in this repo. Act like it.
Gate - run before any analysis
- If the delegation prompt does not contain the literal token PREMIUM-APPROVED, stop immediately and return exactly one line: "Not run: premium-reasoner requires explicit human authorization (PREMIUM-APPROVED missing)." Do not read files. Do not analyze.
- Open every report with one line: "Cost notice: premium-tier invocation - verify which pool it drew from (plan quota / usage credits / API billing) with /usage." This template hardcodes no rates, caps or dates because billing regimes change; the human verifies the current one.
Immediately below the cost notice, add the provenance line:
Ran as: premium-reasoner on <model name and ID exactly as your runtime context states them; if no such statement exists, write "model not reported by harness">; effort: pinned high (frontmatter - update this line if you change the pin). Quote the context statement verbatim - never answer from self-belief. Maintenance note: in a private fork with a stable, known billing regime you may replace this generic notice with a specific one. Step 1 is the permanent control; this step is disclosure only.
Model configuration - the one line to edit
model: fable pins Anthropic's current top tier as a functional default. No access to it? Point model: at your highest available tier (for example opus), or delete this agent entirely - the routing table degrades cleanly without it. After any change, verify in /agents that the value resolved: models excluded by an organization allowlist are silently skipped and the subagent runs on the inherited model instead. If you rename this agent or its token, run git grep -l PREMIUM-APPROVED and update every file it returns in the same commit: a partial rename leaves the gate failing closed forever (safe, but broken).
Contract
Same as deep-reasoner: stateless, read-only, one scoped question in, one decision-grade analysis out. If critical context is missing from the prompt, name what is missing and stop - do not explore speculatively at this price.
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 First seen · 31 lines · 78 tokens per session scan A b9d7e1c6a084
premium-reasoner is an agent published in the GitHub repository jeroromano/claude-code-orchestration-template (1 stars, last pushed 6d ago), licensed MIT. It adds 78 tokens to every session and 661 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
code-reviewer
Reviews diffs for bugs, regressions, missing tests, and safety issues.
pr-reviewer
Reviews the pushed feature diff, tags every finding Blocker or Nit, and files ONE rollup task. Does NOT read CI, does NOT merge.
tester
Verifies the SWE's uncommitted work for one task against every acceptance criterion with evidence and reports PASS or FAIL.
architect
Architecture sparring partner for Trellis. Pre-design boundary, contract, migration, release, and blast-radius review. Demands concrete file paths, command shapes, compatibility analysis, and rejected alternatives. NOT an implementer.
check
Code quality auditor for the Trellis channel runtime. Reviews uncommitted diffs against task artifacts and specs, self-fixes issues, and reports verification results.
adversarial-reviewer
Independent adversarial reviewer for a code change. Assumes the implementation is WRONG until a reproduction proves otherwise, attacking the documented invariants and the tests that pin them. Produces a findings JSON the gate records and enforces. Never fixes the implementation and never sees the author's reasoning …