BD agentguard-burn
Find out what used up a Claude Code or Codex usage limit. Runs `npx agentguard-burn why` on this machine's session transcripts, explains where the tokens went, relays the one "Next:" step it prints, and can install the free AgentGuard plugin that holds runaway sub-agent launches. Use when the user hit their Claude Code or Codex limit, asks where their tokens went, why a session cost so much or ran out so fast, or mentions runaway sub-agents.
Find out what used up a Claude Code or Codex usage limit.
As a process D 46/100 · Unfinished process — weak spots: result and completion, inputs and preconditions, failures and branches
How to improve
- For Hermes the description must be one sentence under 60 characters; move the conditions to a "When to Use" section.
- 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: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-long-hermesdescription is 445 chars; the Hermes authoring standard requires ≤ 60 (one sentence, ending with a period)
Process rating: all ten parameters 46/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 2 mutating operations with no state check
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 60Consistency. The Hermes dialect needs category and tags
- 70When it triggers. States when to use, but not when not to
- 100Steps. 29 steps
- 100Execution cost. Instruction body is 1230 tokens
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
- +1No license
- +2Single-language instructions
- +3Description length 445: enough signal without eating the budget
- +4Structure: 7 headings
- +3Step-by-step instructions: 29 items
- +4Has examples (3 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 78.