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.
git clone --depth 1 https://github.com/tjboudreaux/rosettanpx agentmods add commands/tjboudreaux/rosetta/rosetta-conflictsWrote 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/commands/tjboudreaux/rosetta/rosetta-conflicts)<a href="https://agentmods.dev/commands/tjboudreaux/rosetta/rosetta-conflicts"><img src="https://agentmods.dev/badge/commands/tjboudreaux/rosetta/rosetta-conflicts/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.
<a href="https://agentmods.dev/commands/tjboudreaux/rosetta/rosetta-conflicts"><img src="https://agentmods.dev/badge/commands/tjboudreaux/rosetta/rosetta-conflicts.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00068 | $0.00724 |
| Opus 5.5 | $0.00027 | $0.00290 |
| Sonnet 5.5 | $0.00014 | $0.00145 |
| Haiku 4.5 | $0.00007 | $0.00072 |
Grade A, and why
rosetta-conflicts 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 1mo 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/rosetta-conflicts — audit the decision library for unresolved/stale/contradicted decisions
A decision library is only trustworthy if it uniquely resolves each question. This command finds where
it doesn't — the exact failure that silently produced wrong answers in Rosetta's Phase-0 evals (two
Accepted records for the same thing).
Workflow
1. Conflicts — multiple current records for one query
For each major subsystem/topic (or the user's $ARGUMENTS scope), run the resolver and report any
conflict: true:
python3 scripts/decisions.py resolve --root decisions --text "<topic>" # conflict=true => unresolved
List each conflict with its competing current record ids and recommend the fix (disambiguate by
scope, or supersede the losing side). These are the highest-priority items — a conflicted library
will hand an agent the wrong answer.
2. Code-vs-decision contradictions (truth hierarchy: code wins)
For each Accepted decision, check whether the code it cites still supports it:
decisions.py search --root decisions --status Acceptedto enumerate live records,- read each record's
Sources:paths andgit log -1 -- <path>, - flag any where the current code contradicts the decision (e.g., ADR says Postgres, code imports a cloudsql client) — recommend either updating the code or superseding the ADR.
3. Staleness — cited code moved on
Flag Accepted records whose cited code/commit has changed materially since the record's date (the drift failure mode from the research: silent updates leave a confidently-wrong oracle). Two resolution paths:
- Code moved but the decision still holds → add
Reviewed: <YYYY-MM-DD>to the record (ADR 0027). This acknowledges the code change without corrupting the decision timeline — the staleness guard treatsReviewed:as a re-flaggable baseline, not a permanent override, so any future change re-flags it. Rundecisions.py staleness --root decisionsto see which records need review. - Code moved and the decision is now wrong →
supersedethe ADR with a new one that reflects the current code, or re-runrosettato refresh the library.
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.
- 1mo ago First seen · 50 lines · 68 tokens per session scan A 52fafbbff54e
rosetta-conflicts is a command published in the GitHub repository tjboudreaux/rosetta (5 stars, last pushed 3mo ago), licensed MIT. It adds 68 tokens to every session and 724 once invoked, about $0.0003 per session on Opus 5.5. 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 commands, from other repositories
providers
Check LLM provider status and connectivity.
trace
Check recent LangSmith traces.
unity-doctor
Diagnostic health check — verifies MCP connectivity, .claude/ integrity, Unity project structure, and hook registration.
unity-ralph
Relentless verify-fix loop — refuses to stop until the project is clean. Runs unity-verifier repeatedly with configurable max iterations and stall detection.
unity-audit
Full project health check — meta file integrity, missing references, assembly definition graph, code quality scan, scene hierarchy audit.
unity-optimize
Profile and optimize performance — uses MCP profiler for frame timing, memory, rendering stats. Identifies bottlenecks and applies fixes.