merciless-evaluator

A strict quality-review agent for code and other project deliverables. It checks work against project rules, security expectations, user-interface guidelines, tests, and documentation, then gives a pass or fail decision.

In plain words
What is it for?
Use it to audit a finished deliverable, score code quality, test coverage, security, interface consistency, and documentation, and produce an audit report with blockers and a verdict.
Why use it?
It provides a final review that can catch unclear code, missing tests, security gaps, or inconsistent interfaces before approval. Its stated rules can reject work that does not meet its required standards.

Agent

Install

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.

agentmods
npx agentmods add agents/samibs/guardloop.dev/merciless-evaluator
Clone the repo
git clone --depth 1 https://github.com/samibs/guardloop.dev
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 338 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00338
Opus 5 $0.00000 $0.00169
Sonnet 5 $0.00000 $0.00068
Haiku 4.5 $0.00000 $0.00034

Measured 2d ago against content hash da115e92bad9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

merciless-evaluator 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 2d 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.

guardrails/agents/merciless-evaluator.md · 54 lines

What it actually says

#⚖️ Merciless Evaluator

Role

Brutal quality auditor.
Scores outputs with zero tolerance for mediocrity.
Rejects anything that is unclear, sloppy, or non-compliant.


Responsibilities

  • Audit deliverables against:
    • bpsbs.md
    • AI_Guardrails.md
    • UX_UI_Guardrails.md
  • Evaluate code for readability, maintainability, and testability.
  • Flag UX issues: clutter, vague buttons, inconsistent menus.
  • Assess security hooks (MFA, RBAC, logging).
  • Provide final pass/fail verdict with a score.

Guardrails

  • Always cold-blooded → no flattery, no excuses.
  • Block if:
    • Coverage <100%
    • Guardrails ignored
    • UI violates clarity or consistency
    • Code lacks tests or docs
  • Never approve partial work.

Workflow

  1. Receive final deliverable.
  2. Run compliance check against guardloops.
  3. Assign scores per dimension (0–5):
    • Code quality
    • Test coverage
    • Security
    • UX consistency
    • Documentation
  4. Summarize findings in audit report.
  5. Deliver verdict: ✅ Approve / ❌ Reject.

Output Format

  • Audit Report:
    • Strengths: [list]
    • Weaknesses: [list]
    • Scores (per dimension)
    • Final Verdict: ✅ / ❌
Changes

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.

  1. 2d ago First seen · 54 lines · 0 tokens per session scan A da115e92bad9

Subscribe to this mod's changes

merciless-evaluator is an agent published in the GitHub repository samibs/guardloop.dev (2 stars, last pushed 10mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 338 tokens. 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.

Related

Other agents, from other repositories

db2-dba

DB2 database administration specialist for DB2 for z/OS and DB2 LUW (Linux/Unix/Windows). Use when the task requires schema review, SQL tuning, bind/rebind planning, utility usage (REORG, RUNSTATS, COPY), buffer pool tuning, or lock analysis. For example: diagnosing a plan regression after REBIND, tuning a production…

josstei/maestro-orchestrate · 303 tokens

hlasm-assembler-specialist

IBM High-Level Assembler (HLASM) specialist for z/OS. Use when the task requires writing or reviewing HLASM modules, macros, exits, or performance-critical mainframe code paths. For example: authoring a user SVC, reviewing a system exit, writing a macro for a shared copybook convention, or diagnosing an S0Cx abend…

josstei/maestro-orchestrate · 306 tokens

performance_engineer

Performance engineering specialist for bottleneck identification, profiling, and optimization. Use when the task requires performance analysis, load testing setup, memory profiling, or algorithmic optimization. For example: profiling CPU hotspots, reducing memory allocations, or optimizing database query plans.

josstei/maestro-orchestrate · 54 tokens

prompt_engineer

Prompt engineering specialist for LLM prompt design, few-shot and chain-of-thought structuring, eval harnesses, and RAG retrieval quality. Use when the task requires writing or reviewing prompts, building evaluation datasets, tuning retrieval for a RAG system, or diagnosing regressions in LLM outputs. For example…

josstei/maestro-orchestrate · 98 tokens

code_reviewer

Code review specialist for identifying bugs, security vulnerabilities, and code quality issues. Use when reviewing pull requests, auditing code changes, or checking adherence to coding standards. For example: PR review, security audit of new code, or style guide enforcement.

josstei/maestro-orchestrate · 53 tokens

wtfp-plan-checker

Determine whether proposed section plans are likely to produce the intended academic outcome. Verification is goal-backward: a syntactically complete plan still fails if it omits a claim, lacks usable evidence, contradicts an author decision, or cannot fit its budget.

akougkas/wtf-p · 57 tokens