006-conflict-detection

006-conflict-detection is an agent for coding agents from paulbreuler/limps. It costs 0 tokens per session (521 once invoked), scanned A, original, MIT.

A conflict checker for inherited project context, such as workspace notes and plans passed from one level to another. It looks for contradictions, outdated overrides, broken references, and circular replacement links.

In plain words
What is it for?
Use it to list or validate context conflicts, inspect conflicts for a specific plan, filter by severity, and make CI/CD fail on serious conflicts.
Why use it?
It helps reveal when different documents disagree or refer to information that is no longer valid before those conflicts affect work.

Agent

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/paulbreuler/limps/006-conflict-detection
Clone the repo
git clone --depth 1 https://github.com/paulbreuler/limps

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for 006-conflict-detection

README.md
[![agentmods](https://agentmods.dev/badge/agents/paulbreuler/limps/006-conflict-detection.svg)](https://agentmods.dev/agents/paulbreuler/limps/006-conflict-detection)
Your own site
<a href="https://agentmods.dev/agents/paulbreuler/limps/006-conflict-detection"><img src="https://agentmods.dev/badge/agents/paulbreuler/limps/006-conflict-detection.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 521 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00521
Opus 5 $0.00000 $0.00260
Sonnet 5 $0.00000 $0.00104
Haiku 4.5 $0.00000 $0.00052

Measured 5d ago against content hash 090fbbc53279, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

006-conflict-detection scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plans/0047-limps-context-hierarchy/agents/006-conflict-detection.md · 74 lines

What it actually says

Agent 006: Conflict Detection

Objective

Detect and surface conflicts in inherited context.

Tasks

  1. Conflict detector (src/context/conflicts.ts)

    • Detect direct contradictions (same key, incompatible values)
    • Detect stale overrides (child overrides stale parent)
    • Detect orphan references (refs to superseded/deleted docs)
    • Detect circular supersession
  2. Conflict types

    type ConflictType = 
      | 'direct_contradiction'  // Same key, different values
      | 'stale_override'        // Overriding stale parent
      | 'orphan_reference'      // Refs superseded doc
      | 'circular_supersession' // A → B → A
    
  3. Conflicts CLI

    • limps context conflicts — Show all conflicts
    • limps context conflicts <plan> — Scope to plan
    • limps context conflicts --severity critical — Filter
  4. Validation CLI

    • limps context validate — Exit non-zero if conflicts
    • Useful for CI/CD pipelines
    • --ignore-warnings to only fail on critical

Conflict Output Format

$ limps context conflicts

⚠️ CONFLICT [critical]: Direct contradiction
   workspace.md: database = PostgreSQL
   plan-0042.md: database = SQLite (override)
   Resolution: Using plan value (higher priority)

⚠️ CONFLICT [warning]: Stale override
   plan-0042.md overrides architecture.md
   architecture.md is 25 days old (threshold: 14)
   Recommendation: Review parent document

✗ CONFLICT [critical]: Orphan reference
   plan-0042.md references ADR-0003
   ADR-0003 was superseded by ADR-0010
   Recommendation: Update reference to ADR-0010

Acceptance Criteria

  • All conflict types detected
  • limps context validate fails CI on conflicts
  • Conflicts include resolution/recommendation
  • Severity filtering works
  • Clear output format with context
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 5d ago First seen · 74 lines · 0 tokens per session scan A 090fbbc53279

Subscribe to this mod's changes

006-conflict-detection is an agent published in the GitHub repository paulbreuler/limps (10 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 521 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.