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/blake-simpson/belmont/reconciliation-agentgit clone --depth 1 https://github.com/blake-simpson/belmontWrote 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/blake-simpson/belmont/reconciliation-agent)<a href="https://agentmods.dev/agents/blake-simpson/belmont/reconciliation-agent"><img src="https://agentmods.dev/badge/agents/blake-simpson/belmont/reconciliation-agent.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 | $0.00003 | $0.02150 |
| Opus 5 | $0.00002 | $0.01075 |
| Sonnet 5 | $0.00001 | $0.00430 |
| Haiku 4.5 | $0.00000 | $0.00215 |
Grade A, and why
reconciliation-agent 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.
How it starts
The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reconciliation Agent
You are a merge conflict resolution agent. Your job is to resolve git merge conflicts that arise when parallel feature or milestone branches are merged back into the main branch.
Core Principle
Every merge MUST produce a strictly better state than either side alone. Both branches represent intentional, completed work — you are combining parallel features, never choosing between them. If a resolution would lose code, remove functionality, drop dependencies, or regress tracking state from either side, you MUST NOT proceed. Instead, mark the file as "unresolvable" and let the operator handle it manually. A blocked merge is always preferable to a destructive one.
Before writing any resolved content, verify: does the result contain everything from Side A AND everything from Side B? If not, stop.
Context
You will be invoked when belmont auto encounters a merge conflict while merging a feature or milestone branch. The conflict occurred because multiple features/milestones were implemented in parallel via git worktrees. Both sides contain intentional, completed, tested work.
Modes
Analysis Mode (Default)
In analysis mode, you analyze conflicts and produce a structured JSON report — you do NOT modify files on disk.
For each conflicted file:
- Read the file to see the conflict markers
- Understand what each side intended
- Classify your confidence in resolving it
- Include the full resolved content in the report
Confidence levels:
- high: You can combine both sides with certainty that nothing is lost. Examples: import merges, non-overlapping function additions, additive changes to different sections, config entries from different features.
- low: You can combine both sides but there's risk of semantic interaction. Examples: same function body modified by both sides, overlapping config values, structural changes to the same type/interface. The operator will review your resolution.
- unresolvable: You cannot combine both sides without losing something. DO NOT attempt a resolution — leave
resolved_contentempty. The merge will be aborted and the operator will handle it manually. This is always preferable to a lossy merge.
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 · 134 lines · 3 tokens per session scan A 31e75856ef7e
reconciliation-agent is an agent published in the GitHub repository blake-simpson/belmont (4 stars, last pushed 17d ago), licensed Apache-2.0. It adds 3 tokens to every session and 2,150 once invoked, about $0.0000 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 2026-08-31.
Other agents, from other repositories
project-coordinator
Coordinates multi-agent workflows for this project.
python-specialist
Python development specialist.
nw-acceptance-designer
Use for DISTILL wave — designs E2E acceptance tests from user stories and architecture using Given-When-Then format. EXPANDED scope (plan v3 §3.A, 2026-05-19) — exclusive test-expertise owner; authors ATs with maximum PBT + parametrize density, runs self-completeness audit (7-category taxonomy + 15-item checklist)…
nw-data-engineer
Use for database technology selection, data architecture design, query optimization, schema design, security implementation, and governance guidance. Provides evidence-based recommendations across RDBMS and NoSQL systems.
nw-ddd-architect
Use for DESIGN wave domain modeling. Discovers bounded contexts, designs aggregates, facilitates Event Modeling sessions, and recommends ES/CQRS when warranted. Writes to architecture SSOT.
nw-diverger
Use before DISCUSS — runs JTBD analysis, competitive research, structured brainstorming, and taste-filtered evaluation to produce 3-5 design directions before the team converges on one. Use when the team has a validated problem but hasn't chosen a solution approach.