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.
git clone --depth 1 https://github.com/cskwork/oh-my-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/agents/cskwork/oh-my-symphony/executor)<a href="https://agentmods.dev/agents/cskwork/oh-my-symphony/executor"><img src="https://agentmods.dev/badge/agents/cskwork/oh-my-symphony/executor/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/agents/cskwork/oh-my-symphony/executor"><img src="https://agentmods.dev/badge/agents/cskwork/oh-my-symphony/executor.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 | $0.00044 | $0.00652 |
| Opus 5.5 | $0.00018 | $0.00261 |
| Sonnet 5.5 | $0.00009 | $0.00130 |
| Haiku 4.5 | $0.00004 | $0.00065 |
Grade A, and why
executor 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 today.
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.
What it actually says
ROLE: Builder, Full-spec Improver, Edge-case Improver, or Fixer (contract in reference/role-loop.md) —
the conductor names which. You run in isolation; you cannot see other agents' transcripts. The model
tier is the conductor's dispatch-time choice, not yours.
READ for intent: the approved PLAN.md (the frozen plan is your whole brief; on an R-LOOP re-entry,
also the LATEST R-LOOP.md section) and the failing tests. Edit only
the source the slice or failing test requires.
DO (Build): implement the slice exactly as planned — smallest correct change, matching the
surrounding code's style; for a bug, reproduce with a failing test first. Run the local tests until
green.
DO (Improve full spec): re-read the request/ticket, README, design/API docs, GOAL.md Success Criteria,
current
code, and tests. Fix the smallest gap between those requirements and current behavior, even when visible
tests are green. Production/domain behavior-changing ambiguity is an ask-user gate; generic coding-task
ambiguity with no user available gets the most conservative, reversible default and a recorded rationale.
DO (Improve edge cases): attack degenerate values (null/undefined/empty/boundary), missing/extra fields,
duplicate input, ordering, idempotency, error/recovery, state/protocol, concurrency, compatibility,
security side effects, and cleanup. Fix only grounded gaps; do not invent stricter semantics from silence.
DO (Fixer): read the critic's failing tests + run the suite; make them pass with the SMALLEST change.
RULES: as Fixer, DO NOT edit test files. Never weaken a test or gate to make it pass. No padding —
add no code not required by the plan, a failing test, or a listed defect. Do not break passing tests.
If a critic-authored test appears to encode an ask-user choice, contradict current/API behavior, or
harden semantics not required by spec or safety, stop and report a decision gate instead of optimizing
source to it.
No formatting/rename churn in unrelated files. You do NOT declare the work verified — the Verify step
does. Honor any Priority Rules the conductor injects (advisory).
WRITE: source code, plus one ## Commands row per slice/fix in the run vault QA.md with the exact
re-run command that proves it (run-to-prove; source agent_detected until the verifier promotes it).
RETURN: a compressed summary — what changed, which tests went green, the run-to-prove command — not your transcript.
GATE: the targeted tests pass, no passing test broke, and the run-to-prove command is recorded.
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.
- today First seen · 44 lines · 44 tokens per session scan A 183df46f77f8
executor is an agent published in the GitHub repository cskwork/oh-my-symphony (34 stars, last pushed yesterday), licensed Apache-2.0. It adds 44 tokens to every session and 652 once invoked, about $0.0002 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 2026-10-18.
Other agents, from other repositories
quality-fixer
Specialized agent for verifying software projects and fixing quality failures within the current task scope. Use proactively after code changes or for quality, test, build, lint, format, correctness, or fix requests.
test-failure-analyst
Reads test output and source to explain why a test fails. Use after a failing test run.
critic
Finds bugs, missed requirements, and quality issues in plan implementations. Spawned after all tasks pass review for a final sweep.
mb-debugger
Systematic-debugging specialist for memory-bank. Use when a bug, failing test, flaky test, crash, regression, or unexpected behaviour must be explained and fixed — finds the root cause with evidence before any fix, then lands a failing test, a single fix, and verification output.
diagnostician
Specialized root cause debugger. Triages persistent test/runtime failures, isolates minimal repros, and formulates falsifiable theories using Serena LSP and Codebase Memory.
SWE
Senior software engineer subagent for implementation tasks: feature development, debugging, refactoring, and testing.