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.
npx agentmods add agents/paulbreuler/limps/006-conflict-detectiongit clone --depth 1 https://github.com/paulbreuler/limpsWrote 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.
[](https://agentmods.dev/agents/paulbreuler/limps/006-conflict-detection)<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>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.
| Model | Per session | Once 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 |
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.
What it actually says
Agent 006: Conflict Detection
Objective
Detect and surface conflicts in inherited context.
Tasks
-
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- Detect orphan references (refs to superseded/deleted docs)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
-
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 -
Conflicts CLI
limps context conflicts— Show all conflictslimps context conflicts <plan>— Scope to planlimps context conflicts --severity critical— Filter
-
Validation CLI
limps context validate— Exit non-zero if conflicts- Useful for CI/CD pipelines
--ignore-warningsto 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 validatefails CI on conflicts - Conflicts include resolution/recommendation
- Severity filtering works
- Clear output format with context
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.
- 5d ago First seen · 74 lines · 0 tokens per session scan A 090fbbc53279
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.
Other agents, from other repositories
timps_context_briefing
Get a 3-sentence resumption briefing from the Context Keeper: what you were working on, current state (uncommitted changes, broken tests), and recommended next step. Use when the user says 'what was I doing' or 'catch me up'. Use the timpscontextbriefing MCP tool to perform this task. Do not answer directly — delegate…
domain
How the engineering skills should consume this repo's domain documentation when exploring the codebase.
parallel-implementation-orchestrator
Use this agent when the user requests implementation of design documents or specifications that can be broken down into independent, parallelizable work units. This includes scenarios like:\n\n \nContext: User has completed Phase 1 planning for contextgit and wants to begin implementation.\nuser: "Let's start…
triage-labels
The skills speak in terms of five canonical triage roles. This file maps those roles to the actual label strings used in this repo's issue tracker.
issue-tracker
Issues and PRDs for this repo live as GitHub issues. Use the gh CLI for all operations.
memory-extractor
Automatically extract and save important information from conversations to ContextFS.