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 instructions/broomva/symphony/claude-mdgit clone --depth 1 https://github.com/broomva/symphonyWrote 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/instructions/broomva/symphony/claude-md)<a href="https://agentmods.dev/instructions/broomva/symphony/claude-md"><img src="https://agentmods.dev/badge/instructions/broomva/symphony/claude-md.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 | $0.02865 | $0.02865 |
| Opus 5 | $0.01432 | $0.01432 |
| Sonnet 5 | $0.00573 | $0.00573 |
| Haiku 4.5 | $0.00286 | $0.00286 |
Grade A, and why
symphony CLAUDE.md 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 3d 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 — 241 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md - Symphony
Project
Symphony is a Rust-based orchestration service for coding agents.
See AGENTS.md for architecture, PLANS.md for roadmap, CONTROL.md for quality gates.
Gathering Context
Before starting work, orient yourself using the knowledge graph:
- Read this file and
AGENTS.md— conventions, architecture, obligations - Check project state —
docs/roadmap/Project Status.mdand.planning/STATE.md - Explore relevant docs — traverse
[[wikilinks]]from the entry points:docs/Symphony Index.md— vault navigation hubdocs/architecture/Crate Map.md— which crate owns whatdocs/crates/<crate-name>.md— per-crate API, tests, spec coveragedocs/operations/Configuration Reference.md— WORKFLOW.md formatdocs/operations/Control Harness.md— build gates, test counts
- Check CONTROL.md — setpoints your changes must satisfy
- Check PLANS.md — current phase and remaining tasks
- Check
.planning/REQUIREMENTS.md— spec conformance checklist
When in doubt about behavior, consult the canonical spec: /Users/broomva/Downloads/Symphony SPEC.md.
Commands
make smoke— compile + clippy + test (the gate, runs pre-commit)make check— cargo check + clippymake test— cargo test --workspace (includes CLI integration tests)make build— cargo build --releasemake control-audit— smoke + format check (before PR)make fmt— auto-format codemake install— install binary locally
CLI Testing
Integration tests in tests/cli_integration.rs verify the binary end-to-end:
symphony initscaffolds WORKFLOW.md correctly for both tracker typessymphony validatecatches missing keys, invalid configsymphony configdisplays resolved settings (including pr_feedback, done_state)- Init → Validate round-trip: generated workflows pass validation
- Remote daemon access: auth rejection works properly
- Error paths: missing files, unsupported trackers, overwrite protection
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.
- 3d ago First seen · 241 lines · 2,865 tokens per session scan A b170aa8e11f3
symphony CLAUDE.md is an instructions file published in the GitHub repository broomva/symphony (9 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 2,865 tokens to every session, about $0.0143 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 instructions, from other repositories
autoany CLAUDE.md
Instructions for broomva/autoany, covering autoany — egri framework, project structure, commands, adapter crates (standalone, not in workspace) and architecture rules.
sample-autonomous-cloud-coding-agents AGENTS.md
AGENTS.md instructions for aws-samples/sample-autonomous-cloud-coding-agents, covering agents.md, your role, commands (run these), git workflow and where to make changes.
sample-autonomous-cloud-coding-agents CLAUDE.md
Claude Code instructions for aws-samples/sample-autonomous-cloud-coding-agents, a project described as: Autonomous background coding agents on AWS. Turn tasks into pull requests via isolated runtimes, with built-in orchestration, observability, and governance.
helmor AGENTS.md
Instructions for dohooo/helmor, covering agents.md, what is helmor, commands, architecture and three-process model.
OwnPilot AGENTS.md
Instructions for ownpilot/OwnPilot, covering ownpilot, architecture, key patterns, commands and tech stack.
zeroshot AGENTS.md
AGENTS.md instructions for the-open-engine/zeroshot, covering zeroshot: multi-agent coordination engine, critical rules, where to look, cluster worker contracts and cli quick reference.