AC agent-harness
Production-grade Agent Harness combining execution discipline, knowledge compounding, and product thinking into a single adaptive workflow. Use when: (1) building features or fixing bugs with AI agents, (2) user says 'build', 'plan', 'spec', 'review', 'ship', 'debug', (3) managing multi-step or multi-agent tasks, (4) need structured engineering workflow with quality gates. Provides: task complexity auto-grading (simple/medium/complex), anti-rationalization guards, concurrent subagent scheduling (≤4 hard limit), tool-chain continuity enforcement, context budget management, verification protocols, and experience compounding. Triggers: 'agent harness', 'engineering workflow', 'build protocol', 'multi-agent task', 'coding discipline', 'subagent orchestration'.
As a process C 57/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
How to improve
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 4. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 57/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 40Result and completion. Does not say what the result is
- 40Consistency. Frontmatter name (agent-harness) differs from the folder (trinity-harness)
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 100Steps. 76 steps
- 100Failures and branches. 2 branches, has a failure section
- 100Execution cost. Instruction body is 2440 tokens
- 100Running it twice. Mutating operations check current state
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 14 top-level sections: this looks like several domains in one skill
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- -5TODO / placeholder text left in the skill
- -224 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +3Description length 766: enough signal without eating the budget
- +4Structure: 21 headings
- +3Step-by-step instructions: 76 items
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.