loop-budget

Check token budget and run-log spend before and after a loop run. Enforces early exit when over budget or when there is no actionable work.

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

93%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a tight, highly actionable decision procedure with exact thresholds, named state files, and a concrete log schema, all well-organized under 50 lines. The only soft spot is the absence of an explicit error-recovery feedback loop, which leaves workflow clarity just short of perfect.

Dimension	Reasoning	Score
Conciseness	Lean and efficient at ~40 lines: assumes Claude knows the domain, references state files without explaining them, and every line (threshold rules, JSON schema) earns its place with no concept padding.	5 / 5
Actionability	Fully executable guidance: exact threshold percentages (80/90/100%), named files to read, defined modes (report-only, exit), and a copy-paste-ready JSON log schema with concrete fields covering the common logging case.	5 / 5
Workflow Clarity	Clear two-phase sequence (Start of run / End of run) with explicit conditional checkpoints at each spend threshold; not a 5 because there is no explicit validate->fix->retry feedback loop for error recovery.	4 / 5
Progressive Disclosure	Under 50 lines, single-purpose, with well-organized sections (Start, End, Rules); the only referenced files are runtime state/data files, not nested documentation tiers, so navigation is unambiguous.	5 / 5
	Total	19 / 20 Passed

Description

73%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is concise, third-person, and clearly communicates a distinct niche (budget guarding for loops) with concrete actions and reasonable trigger terms. Its main gap is the lack of an explicit "Use when..." trigger phrase and only modest action coverage.

Suggestions

Add an explicit trigger clause, e.g. "Use when running a budgeted loop iteration or before spawning loop sub-agents." to push completeness toward 5.

Enumerate a couple more concrete actions (e.g. "appends a run-log entry", "throttles sub-agent spawns") to lift specificity from 3 to 4-5.

Include a common synonym or phrasing users might say (e.g. "token cost" or "spend limit") to round out trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ("token budget and run-log spend") and 2 concrete actions ("Check ... spend before and after a loop run", "Enforces early exit"), but does not list several distinct actions, fitting the 1-2-concrete-actions anchor rather than the comprehensive one.	3 / 5
Completeness	Clearly states what it does and gives when guidance via "before and after a loop run" plus condition "when over budget or when there is no actionable work", which serves as equivalent trigger guidance; not a 5 because there is no explicit "Use when..." phrase with concrete user-need triggers.	4 / 5
Trigger Term Quality	Good coverage of natural domain terms a user would say ("token budget", "over budget", "loop run", "actionable work", "early exit"), with only minor synonyms missing; better than the bare-keyword anchor 3 but not fully comprehensive enough for a 5.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (budget guard for loop runs) with distinct triggers ("loop run", "token budget", "run-log spend") and minimal overlap risk with other skills.	5 / 5
	Total	16 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 1 suspicious	Warning

	Total	15 / 16 Passed

Repository: cobusgreyling/loop-engineering
Path: skills/loop-budget/SKILL.md
Commit: 804a4e9

Reviewed: about 12 hours ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.