CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

63

Quality

73%

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

Fix and improve this skill with Tessl

tessl review fix ./plugins/orchestrator-discipline/skills/orchestrator-discipline/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

62%

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

This skill provides a well-structured description of orchestrator discipline enforcement with clear workflow sequencing and specific trigger patterns. Its main weaknesses are moderate redundancy between sections and a lack of executable setup/configuration code — it describes the system's behavior thoroughly but doesn't show how to install or configure the hooks. The progressive disclosure is adequate but could benefit from splitting detailed trigger patterns into a reference file.

Suggestions

Add executable code examples showing how to configure or install the PreToolUse hooks (e.g., the actual hook function signatures or configuration file snippets)

Consolidate the hook descriptions — remove the summary in 'What This Plugin Provides' section 1 and keep only the detailed 'Hook Behavior Reference' section to eliminate redundancy

Move the detailed trigger pattern lists (file extensions, command patterns) into a separate reference file like `references/hook-patterns.md` and link from the main SKILL.md

DimensionReasoningScore

Conciseness

The content is moderately 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 avoids explaining basic concepts Claude would know.

2 / 3

Actionability

The skill describes what the hooks do and when they trigger with specific patterns and file extensions, which is concrete. However, it lacks executable setup instructions — there's no code showing how to install/configure the hooks, no example hook implementation, and the mermaid diagram is descriptive rather than actionable. It tells Claude what the system does rather than giving copy-paste-ready configuration.

2 / 3

Workflow Clarity

The mermaid flowchart clearly sequences the correct orchestrator workflow with decision points, and explicitly marks the wrong path. The hook behavior reference provides clear trigger conditions and non-trigger exceptions. The blocking vs non-blocking distinction is well-documented with explicit behavioral outcomes (exit code 2).

3 / 3

Progressive Disclosure

There is one reference to an external file (investigation-escalation.md) and a mention of rules/CLAUDE.md, but no bundle files are provided to verify these exist. The content is somewhat monolithic — the detailed hook trigger patterns could be split into a reference file, with the SKILL.md providing just the overview. The structure is reasonable but the inline detail is heavy for a top-level skill file.

2 / 3

Total

9

/

12

Passed

Description

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 strong description that clearly articulates specific capabilities and explicit trigger conditions for a well-defined niche. The 'what' and 'when' are both thoroughly addressed, and the skill occupies a distinct space unlikely to conflict with others. The main weakness is that trigger terms lean technical, which could limit matching when users describe the problem in more natural language.

Suggestions

Consider adding more natural-language trigger phrases like 'orchestrator reading too many files', 'agent wasting tokens', or 'subagent not being delegated to' to improve matching with how users might describe these problems.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions: prevents reading unedited source files, blocks wasteful diagnostic commands, prevents delegation bypass rationalization, 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').

3 / 3

Trigger Term Quality

Includes relevant terms like 'orchestrator', 'context window', 'delegation', 'multi-agent workflows', and 'PreToolUse hooks', but these are fairly technical. Missing more natural user phrases like 'agent running out of context', 'subagent not being used', or 'orchestrator reading too many files'.

2 / 3

Distinctiveness Conflict Risk

Highly distinctive niche targeting orchestrator context window discipline specifically, with unique triggers like 'PreToolUse hooks', 'delegation bypasses', and 'context window waste'. Unlikely to conflict with other skills.

3 / 3

Total

11

/

12

Passed

Validation

100%

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

Validation11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository
Jamie-BitFlight/claude_skills
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.