What is conflict-detector?

A conflict checker for proposed tasks and pending related tasks. It detects overlapping files and overlapping functions or code regions; more advanced semantic and architectural checks are currently stubs.

Use it when dispatching T4 tasks alongside pending sibling tasks. It checks file overlap first, then examines the affected code regions when needed.

It can catch two tasks trying to change the same code before work is dispatched. This helps reduce collisions between parallel tasks while clearly limiting checks that are not yet implemented.

conflict-detector — Skill for Claude Code by nguyenthienthanh

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo

git clone --depth 1 https://github.com/nguyenthienthanh/aura-frog

agentmods

npx agentmods add skills/nguyenthienthanh/aura-frog/conflict-detector

Made for: Claude Code.

Or install aura-frog, the plugin that ships this one along with the rest of its 43 skills, 24 commands, 15 agents, 10 hooks, 6 MCP servers.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/nguyenthienthanh/aura-frog/conflict-detector/github.svg)](https://agentmods.dev/skills/nguyenthienthanh/aura-frog/conflict-detector)

Your own site

<a href="https://agentmods.dev/skills/nguyenthienthanh/aura-frog/conflict-detector"><img src="https://agentmods.dev/badge/skills/nguyenthienthanh/aura-frog/conflict-detector/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/nguyenthienthanh/aura-frog/conflict-detector"><img src="https://agentmods.dev/badge/skills/nguyenthienthanh/aura-frog/conflict-detector.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 84 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,572 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

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.

Model	Per session	Once invoked
Fable 5.1	$0.00084	$0.01572
Opus 5	$0.00042	$0.00786
Sonnet 5	$0.00017	$0.00314
Haiku 4.5	$0.00008	$0.00157

Measured 10d ago against content hash 97a98fa0a707, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

conflict-detector 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 10d 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.

aura-frog/skills/conflict-detector/SKILL.md · 122 lines

How it starts

The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI-consumed reference. Optimized for Claude to read during execution. Human-readable explanation: see docs/architecture/HIERARCHICAL_PLANNING.md or docs/getting-started/ depending on topic.

Conflict Detector

STATUS — v3.7.0-beta.2. L1+L2 functional; L3+L4 stubbed pending LLM-dispatch infrastructure in rc.1.

Five conflict types (per spec §21.1)

types[5]{type,definition,detection_layer,cost}:
  C1,File-level overlap,L1,free
  C2,Function/region overlap,L2,cheap (~10ms regex)
  C3,Schema/contract conflict,L2,cheap
  C4,Semantic intent conflict,L3,LLM (stubbed in beta.2)
  C5,Architectural conflict,L4,LLM-rare (stubbed in beta.2)

Layer dispatch (per spec §21.3)

ON dispatch_request(task):
    L1 = check-l1-files.sh         ← always run, free
    IF L1.overlap AND L1.confidence >= 0.95:
      RETURN conflict(L1)
    IF L1.overlap (low confidence):
      L2 = check-l2-syntactic.sh   ← drill into overlapping files
      IF L2.overlap:
        RETURN conflict(L2)

    IF task.tier <= 2 OR task.creates_new_pattern:
      L4 = check-architectural (LLM, stubbed)  ← skipped in beta.2
      IF L4.contradicts: RETURN conflict(L4)

    IF task.parent has any pending-confirm sibling:
      L3 = check-semantic (LLM, stubbed)       ← skipped in beta.2
      IF L3.contradicts: RETURN conflict(L3)

    RETURN clear

Disable

Set AF_CONFLICT_LLM_DISABLED=true to short-circuit L3+L4 dispatch even after they land in rc.1+ — useful for cost-sensitive sessions. L1+L2 (deterministic bash) always run; the env var only affects the LLM-backed layers. In v3.7.0-beta.2 / rc.1 it is effectively a no-op because L3+L4 are already stubbed; documented for forward compatibility with v3.7.x patch releases.

Behavior

Resolve proposed task's artifacts[].path from its plan node frontmatter
Resolve pending-confirm siblings (status: planned with parent T3 active, or status: blocked-on-confirm)
Run scripts/conflicts/check-l1-files.sh with task + siblings artifact lists
If L1 returns overlap with confidence < 0.95 OR file-overlap is ambiguous → run check-l2-syntactic.sh on the overlapping files
L3 (semantic): in beta.2, return {layer:L3, status:stubbed_for_rc1}. In rc.1, dispatch an LLM call comparing intents; cache result in conflict_cache.jsonl.
L4 (architectural): in beta.2, return {layer:L4, status:stubbed_for_rc1}. In rc.1, dispatch an LLM call comparing against permanent_memory.md decisions.
Append finding to .claude/plans/conflicts.jsonl (per spec §21.4) if conflict found

Read the full file on GitHub · 122 lines

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.

10d ago First seen · 122 lines · 84 tokens per session scan A 97a98fa0a707

Subscribe to this mod's changes

conflict-detector is a skill published in the GitHub repository nguyenthienthanh/aura-frog (24 stars, last pushed 6d ago), licensed MIT. It adds 84 tokens to every session and 1,572 once invoked, about $0.0004 per session on Opus 5. 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 2026-08-30.

Claude Code Project management ai-assisted-development ai-for-developers code-quality context-engineering developer-productivity

conflict-detector

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Conflict Detector

Five conflict types (per spec §21.1)

Layer dispatch (per spec §21.3)

Disable

Behavior

What this file has done since we first saw it

Other skills, from other repositories

resume_handoff

create_handoff

feature

gsd-manager

gsd-new-project

gsd-resume-work