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/kwanpham2195/symphony-go/agents-mdgit clone --depth 1 https://github.com/kwanpham2195/symphony-goWrote 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/kwanpham2195/symphony-go/agents-md)<a href="https://agentmods.dev/instructions/kwanpham2195/symphony-go/agents-md"><img src="https://agentmods.dev/badge/instructions/kwanpham2195/symphony-go/agents-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 5.1 | $0.02021 | $0.02021 |
| Opus 5 | $0.01010 | $0.01010 |
| Sonnet 5 | $0.00404 | $0.00404 |
| Haiku 4.5 | $0.00202 | $0.00202 |
Grade A, and why
symphony-go AGENTS.md scanned grade A with 1 finding 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 6d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s -X POST https://api.linear.app/graphql \ How it starts
The opening of the file, as written. The whole thing — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Go implementation of Symphony — a scheduler/runner that polls Linear, creates per-issue workspaces, and runs Codex app-server sessions.
Build / Test
make check # full CI gate: golangci-lint + go test -race (matches CI exactly)
make check-sandbox # sandbox-safe: lint + unit tests only (no network-binding acceptance tests)
make build # build binary
Run a single package:
go test ./internal/orchestrator/...
Validate a workflow file without starting the service:
LINEAR_API_KEY=... go run ./cmd/symphony --validate-only ./testdata/workflows/minimal.md
Architecture
| Package | Owns |
|---|---|
cmd/symphony |
CLI entry point. Wires all components. |
internal/*.go |
Shared types: Issue, Workspace, Workflow, AgentUpdate, etc. |
internal/config |
Typed config from WORKFLOW.md front matter. Defaults, $VAR env, ~ expansion, validation. |
internal/workflow |
WORKFLOW.md parser (YAML front matter + body). Liquid prompt renderer. fsnotify watcher. |
internal/tracker |
Tracker interface (read-only). |
internal/tracker/linear |
Linear GraphQL client. Pagination, normalization, ExecuteGraphQL. |
internal/workspace |
Per-issue workspace lifecycle: create/reuse/remove, path safety, hooks. |
internal/codex |
Codex app-server JSON line protocol client. |
internal/codex/tools |
Dynamic tools (linear_graphql). |
internal/orchestrator |
Poll loop, dispatch, retry/backoff, reconciliation, snapshot. Depends on interfaces only. |
internal/runner |
Agent runner glue: workspace + prompt + codex. |
internal/server |
HTTP dashboard and JSON status API. |
internal/worker |
Local + SSH launcher, worker pool with capacity tracking. |
The orchestrator depends on interfaces (Tracker, WorkspaceManager, AgentRunner), not concrete types. Tests use fakes.
See ARCHITECTURE.md for the full system overview.
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.
- 6d ago First seen · 147 lines · 2,021 tokens per session scan A 631fe8f9f7a7
symphony-go AGENTS.md is an instructions file published in the GitHub repository kwanpham2195/symphony-go (10 stars, last pushed 3mo ago), licensed MIT. It adds 2,021 tokens to every session, about $0.0101 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
emdash AGENTS.md
AGENTS.md instructions for generalaction/emdash, covering project overview, repository structure, build & development commands, code style & conventions and architecture notes.
personal-agent-template AGENTS.md
AGENTS.md instructions for vercel-labs/personal-agent-template, covering personal agent template, quick reference, structure, documentation and eve framework.
linear-cli AGENTS.md
AGENTS.md instructions for schpet/linear-cli, covering basics, permissions, error handling, cli flags and tests.
cyrus copilot-instructions.md
Copilot instructions for cyrusagents/cyrus: Note, there is a need to maintain the use of '--print' when running the claude exec commands because that is what makes it non-interactive.
streamlinear CLAUDE.md
Instructions for prime-radiant-inc/streamlinear, covering claude.md, what this is, setup, common commands and build artifacts.
streamlinear AGENTS.md
Instructions for prime-radiant-inc/streamlinear, covering agents.md, project, setup, verification and build artifacts.