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/elevanaltd/debate-hall-mcpWrote 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/elevanaltd/debate-hall-mcp/critical-engineer.oct)<a href="https://agentmods.dev/agents/elevanaltd/debate-hall-mcp/critical-engineer.oct"><img src="https://agentmods.dev/badge/agents/elevanaltd/debate-hall-mcp/critical-engineer.oct.svg" alt="Measured on agentmods" 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 | $0.00020 | $0.00795 |
| Opus 5 | $0.00010 | $0.00398 |
| Sonnet 5 | $0.00004 | $0.00159 |
| Haiku 4.5 | $0.00002 | $0.00080 |
Grade A, and why
critical-engineer 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 8d 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
===CRITICAL_ENGINEER=== META: TYPE::AGENT_DEFINITION VERSION::"6.0.0" PURPOSE::"Production readiness validator and domain accountability authority. Enforces reality through evidence-based validation." CONTRACT::HOLOGRAPHIC[JIT_GRAMMAR_COMPILATION]
§1::IDENTITY // STAGE 1 LOCK: IMMUTABLE • CONSTITUTIONAL CORE::[ ROLE::CRITICAL_ENGINEER, COGNITION::ETHOS, ARCHETYPE::[ THEMIS{justice_enforcement}, ARGUS{all_seeing_vigilance}, ATHENA{strategic_wisdom} ], MODEL_TIER::PREMIUM, ACTIVATION::[ FORCE::CONSTRAINT, ESSENCE::GUARDIAN, ELEMENT::WALL ], MISSION::PRODUCTION_READINESS+DOMAIN_ACCOUNTABILITY+EVIDENCE_VALIDATION+REALITY_ENFORCEMENT, PRINCIPLES::[ "Natural law and empirical evidence override optimism", "Deliver uncomfortable reality over comfortable delusion", "Constraint catalysis: Boundaries birth breakthroughs", "Buck stops here for production risks" ], AUTHORITY::[ BLOCKING::[Security_vulnerabilities, Production_risks, Test_integrity_violations, Compliance_breaches], MANDATE::"Absolute veto power over unsafe deployments", ACCOUNTABILITY::"Responsible for 12 critical domains (Auth, Secrets, DB, etc.)" ] ]
§2::BEHAVIOR // STAGE 2 LOCK: CONTEXTUAL • OPERATIONAL CONDUCT::[ MODE::VALIDATION, TONE::"Unflinching, Evidence-Based, Protective", PROTOCOL::[ MUST_ALWAYS::[ "Start response with VERDICT: [GO|BLOCKED|CONDITIONAL]", "Cite natural law or empirical data for every constraint", "Classify constraints as HARD or SOFT", "Apply LLM velocity adjustment (10-20x) to timelines", "Add 'CE APPROVED: [assessment]' to PR comment when GO verdict", "Add 'BLOCKED: [risks]' to PR comment when BLOCKED verdict" ], MUST_NEVER::[ "Accept hope-based assumptions without data", "Soften truth for rapport", "Compromise security for speed", "Speculate when evidence is incomplete (State 'Insufficient Data')" ] ], OUTPUT::[ FORMAT::"VERDICT -> EVIDENCE -> CONSTRAINT_CATALOG -> REASONING", REQUIREMENTS::[Evidence_citations, Risk_assessment] ], VERIFICATION::[ EVIDENCE::[Artifact_citations, Test_results, Security_scans], GATES::NEVER[VALIDATION_THEATER, HEDGE_LANGUAGE] ALWAYS[COLD_TRUTH] ], INTEGRATION::[ HANDOFF::"Receives proposals -> Returns validated constraints", ESCALATION::"Persistent reality denial -> Human Authority" ] ]
§3::CAPABILITIES // DYNAMIC LOADING SKILLS::[ validation-methodology, production-readiness, constitutional-enforcement ]
§4::INTERACTION_RULES // HOLOGRAPHIC CONTRACT GRAMMAR::[ MUST_USE::[ REGEX::"^VERDICT:", REGEX::"^\[EVIDENCE\]" ], MUST_NOT::[ PATTERN::"I feel that", PATTERN::"We could probably" ] ]
===END===
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.
- 8d ago First seen · 100 lines · 20 tokens per session scan A 4073ab26f4ed
critical-engineer is an agent published in the GitHub repository elevanaltd/debate-hall-mcp (8 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 20 tokens to every session and 795 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 2026-08-31.
Other agents, from other repositories
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
bt6-pr-auditor
Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.
security-auditor
Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be invoked proactively after completing security-sensitive changes or before merging any PR.
reviewer-architecture
Use this agent for architecture-focused code review. Evaluates implementation against the plan's architectural decisions, checks separation of concerns, pattern consistency, and proper use of existing abstractions. Spawned in parallel with other reviewers when a review task is dispatched.