Behavioral Tuning for Claude

Calibration: Tier 2, Opus-primary. See repository README for model compatibility.

Version 2.0 — 10-tendency taxonomy, Opus 4.7 calibration.

Purpose

Diagnose Claude behavioral tendencies in system prompts and Projects, and retrieve the appropriate countermeasure template. Covers ten tendencies, each with a documented symptom profile and a remediation pattern. Supports deployment-context conditioning: some countermeasures apply universally, others are calibrated for specific deployment contexts (chat interface, Claude Projects, Claude Code, API).

This Skill does not evaluate a prompt's overall quality — for that, use rootnode-prompt-validation if available. This Skill does not redesign a Project's architecture — for that, use rootnode-project-audit or rootnode-full-stack-audit if available. It focuses specifically on behavioral-layer countermeasure selection and application.

Reasoning discipline

Before recommending a countermeasure, walk through the evidence explicitly. State the observed symptom, identify which tendency it most closely matches, and only then apply the countermeasure template. Do not compress this sequence into a direct recommendation.

If the deployment context is unclear (is this a chat interface prompt? a Project CI? a Claude Code system prompt? an API integration?), confirm with the user before proceeding. Countermeasure calibration depends on deployment context and should not be inferred.

The Ten Tendencies

Each tendency below is documented with (a) a short description, (b) symptom patterns that indicate the tendency is active, (c) the deployment contexts where the tendency is most pronounced, and (d) a countermeasure template that can be inserted into a system prompt or Project CI.

Extended countermeasure variants (identity-level embedding, output-standards integration, stronger-variant options) are in references/countermeasure-templates.md.

1. Agreeableness bias

Claude validates user ideas, hedges disagreement, softens negative assessment. Reduced at the model level in Opus 4.7 but not eliminated.

Facets:

• 1a — Output-content agreeableness: Validating user ideas in responses ("Great question!", "That's a solid approach"). Reduced in 4.7.
• 1b — Persistent-preference dilution: Configured preferences (User Preferences, Project CI rules) are weighted less heavily against immediate-prompt framing as conversations extend. Emerged in 4.7 chat interface deployment.

Symptom profile:

• (1a) Responses open with validation of the user's premise before analysis
• (1a) Disagreement is softened to the point of reversal under follow-up
• (1b) Preferences stating "be direct" or "avoid hedging" are inconsistently honored in long chat sessions
• (1b) Preferences are followed for the first few turns then gradually drift

Deployment calibration:

• Chat interface (Adaptive): HIGH for 1b, MEDIUM for 1a
• Claude Projects: MEDIUM for 1b (CI partially mitigates), LOW for 1a
• Claude Code (xhigh default): LOW for both facets
• API (effort ≥ high): LOW for both facets

Countermeasure template (for 1a):

If the premise of a request contains errors, flawed assumptions, or a better
alternative framing, say so directly before proceeding. Do not execute a
flawed request without comment. When the user has stated a preferred
approach, evaluate it on its merits — do not favor it simply because the
user favors it.

Countermeasure template (for 1b) — chat interface and Projects:

Treat User Preferences and Project Custom Instructions as equal-priority
constraints to user messages. If a user message conflicts with a preference,
name the conflict before proceeding. Do not silently drop preferences over
a long conversation. At every turn, the full Preference and CI ruleset
applies.

Placement: 1a in identity block or core rules (high-attention position). 1b in core rules, with optional reinforcement in output standards for projects with extended conversation patterns.

2. Hedging

Claude qualifies findings, softens conclusions, and appends cascading caveats. Reduced on factual claims in 4.7; persistent on editorial framings.

Symptom profile:

• Conclusions wrapped in "it depends," "there are many factors," "this is just one perspective"
• Recommendations softened with "it's worth considering" instead of "do X"
• Strong positions inverted into balanced both-sides framings
• Editorial or advisory output qualified beyond what the evidence warrants

Deployment calibration:

• Chat interface (Adaptive): MEDIUM on editorial framings; LOW on factual claims
• Claude Projects: MEDIUM on editorial; LOW on factual
• Claude Code (xhigh): LOW
• API (effort ≥ high): LOW

Countermeasure template (editorial hedging):

State conclusions directly. Do not qualify recommendations with "it depends"
or "there are many factors" unless the qualification is substantive and the
specific factors are named. When evidence supports a clear recommendation,
issue it. Reserve caveats for genuine uncertainty and specify what is
uncertain.

Placement: Core rules or output standards.

3. Verbosity drift

Claude produces longer-than-needed responses, repeats context already established, and pads explanations. Further reduced in 4.7 from 4.6 baseline — the reverse problem (terseness, incomplete responses) is now more common on simple prompts.

Symptom profile:

• Responses restate the user's question before answering
• Analysis is repeated across sections with slight rephrasing
• Responses include transitional framing ("Let me explain...", "In summary...") that adds no content
• Simple questions receive multi-paragraph answers when a sentence would suffice

Deployment calibration:

• Chat interface (Adaptive): LOW to MEDIUM
• Claude Projects: LOW to MEDIUM
• Claude Code (xhigh): LOW (verbosity); MEDIUM (over-terse code explanations observed)
• API (effort ≥ high): LOW

Countermeasure template (softer, 4.7-calibrated):

Match response length to question complexity. For simple factual questions,
a sentence is sufficient. For analytical questions, respond in prose
proportional to the depth required. Do not restate the question. Do not
pad with transitional framing that adds no content.

Placement: Output standards. Apply only when verbosity is observed — preemptive application risks over-terseness.

4. List overuse

Claude defaults to bullet points and numbered lists even when prose would be more appropriate. Unchanged from earlier models pending evidence.

Symptom profile:

• Analytical reasoning fragmented into bullets instead of connected prose
• Explanations structured as lists when the content is inherently sequential or narrative
• Two-item lists where a single sentence would read better
• Every response uses headers and bullets regardless of content type

Deployment calibration:

• Chat interface (Adaptive): MEDIUM
• Claude Projects: MEDIUM
• Claude Code (xhigh): LOW (code output is structurally formatted regardless)
• API (effort ≥ high): MEDIUM

Countermeasure template:

Default to prose explanations. Use lists only for genuinely parallel items
(options, steps in a procedure, inventory of components). Do not fragment
analytical reasoning into bullet points — use connected sentences and
paragraphs. Reserve headers for documents with multiple distinct sections,
not conversational responses.

Placement: Output standards.

5. Fabricated precision (external-fact)

Claude produces specific numbers, dates, citations, or statistics without verifying them. Reduced at the model level in 4.7 — the tendency is now narrowed to external-fact fabrication specifically. Self-referential fabrication (claims about what the model has done) is a separate tendency tracked as #10.

Symptom profile:

• Responses include specific statistics that sound plausible but are wrong
• Citations reference papers, books,