orchestrator-discipline
Orchestrator context window discipline enforcement. Prevents the orchestrator from reading source files it will not edit, running diagnostic commands that waste context, and rationalizing delegation bypasses. Use when setting up orchestrator guardrails, reviewing delegation discipline, or diagnosing context window waste in multi-agent workflows. Activates PreToolUse hooks that surface decision points before source file reads and diagnostic command execution.
62
73%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/orchestrator-discipline/skills/orchestrator-discipline/SKILL.mdQuality
Discovery
85%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a well-crafted description that clearly defines a specific niche (orchestrator context window discipline), lists concrete preventive actions, and includes an explicit 'Use when' clause with multiple trigger scenarios. Its main weakness is that the trigger terms lean toward technical jargon that may not match how users naturally phrase their needs, though given the technical nature of the skill's domain, this is somewhat expected.
Suggestions
Consider adding more natural-language trigger variations such as 'agent reading too many files', 'subagent not delegating', or 'token usage too high' to improve discoverability for users who may not use the precise technical terminology.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: prevents reading unedited source files, blocks wasteful diagnostic commands, prevents delegation bypass rationalizations, and activates PreToolUse hooks for decision points. These are clearly defined, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both what ('Prevents the orchestrator from reading source files it will not edit, running diagnostic commands...') and when ('Use when setting up orchestrator guardrails, reviewing delegation discipline, or diagnosing context window waste in multi-agent workflows'). The explicit 'Use when' clause with multiple trigger scenarios is present. | 3 / 3 |
Trigger Term Quality | Includes some relevant terms like 'orchestrator', 'context window', 'delegation', 'multi-agent workflows', and 'guardrails', but these are somewhat technical/jargon-heavy. A user might more naturally say 'agent is reading too many files' or 'subagent keeps doing work itself' rather than 'context window discipline enforcement'. | 2 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche focused specifically on orchestrator context window discipline and PreToolUse hooks in multi-agent workflows. This is unlikely to conflict with other skills due to its very specific domain of orchestrator guardrails and delegation discipline. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
62%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill effectively communicates orchestrator discipline concepts with a clear workflow diagram and well-defined hook trigger patterns. Its main weaknesses are moderate redundancy between the overview and reference sections, and the lack of executable configuration examples for setting up or customizing the hooks. The progressive disclosure could be improved by moving the detailed hook behavior reference to a separate file.
Suggestions
Add executable configuration examples showing how hooks are defined (e.g., the actual hook registration code or config file), rather than only describing trigger behavior
Move the detailed 'Hook Behavior Reference' section to a separate file (e.g., HOOKS_REFERENCE.md) and link to it from the main SKILL.md to reduce inline bulk
Consolidate the hook descriptions — the 'What This Plugin Provides' section and 'Hook Behavior Reference' section overlap significantly; present the information once
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is reasonably efficient but includes some redundancy — the hook behavior reference section repeats information already covered in the 'What This Plugin Provides' section. The SOURCE citations and some explanatory text could be tightened. However, it largely avoids explaining concepts Claude already knows. | 2 / 3 |
Actionability | The skill provides concrete trigger patterns and a clear mermaid workflow diagram, but lacks executable code examples for hook implementation or configuration. The hook descriptions tell what happens but don't show how to set them up or modify them. The trigger patterns are specific but presented descriptively rather than as executable configurations. | 2 / 3 |
Workflow Clarity | The mermaid flowchart clearly sequences the correct orchestrator workflow with decision points. The distinction between blocking and non-blocking hooks is explicit. The anti-pattern is visually marked as WRONG in the diagram, and the escalation path is clearly documented. Validation is implicit in the hook system itself (structural enforcement via exit code 2). | 3 / 3 |
Progressive Disclosure | There is one reference to an external file (investigation-escalation.md) and mention of rules/CLAUDE.md, but no bundle files were provided to verify these exist. The hook behavior reference section is quite detailed and could potentially be split into a separate reference file. The structure is reasonable but the inline detail is heavy for a SKILL.md overview. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- Jamie-BitFlight/claude_skills
- Commit
4e61312
- Reviewed
Table of Contents
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.