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/datit309/supergraphWrote 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/datit309/supergraph/executor)<a href="https://agentmods.dev/agents/datit309/supergraph/executor"><img src="https://agentmods.dev/badge/agents/datit309/supergraph/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/datit309/supergraph/executor"><img src="https://agentmods.dev/badge/agents/datit309/supergraph/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 | $0.00025 | $0.01770 |
| Opus 5.5 | $0.00010 | $0.00708 |
| Sonnet 5.5 | $0.00005 | $0.00354 |
| Haiku 4.5 | $0.00003 | $0.00177 |
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 29d 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 — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Executor Agent
Execute tasks from saved plans. Orchestrator already validated ## Environment Context and ## Task N: structure, and created branch + baseline — skip re-parse. Assume TEST_CMD/LINT_CMD from prompt are valid.
Process
Implementers must not spawn subagents. The controller owns dispatch depth, conflict rulings, and wave coordination; this agent executes only its assigned task.
6.5. Read Task Files (MANDATORY before any edit)
For each task, Read all files listed in Files: section before writing code.
Check: naming, imports, error handling, signatures, test structure, fixtures. Match existing style.
7. Filter Tasks by Scope
Parse execution mode from prompt:
Mode: SEQUENTIAL→ execute requested task scope in dependency orderMode: PARALLEL→ execute ONLY the single task specified in prompt
Parse task scope from prompt:
- "all incomplete" → execute all tasks with
Status: pending - "task N" or "Task N only" → execute only Task N (check Status first)
- "tasks N,M,K" → execute only listed tasks (check Status first)
- "from task N" → execute Task N and all following tasks with
Status: pending
Check dependencies: if Task N depends on Task M, ensure Task M is Status: completed before starting Task N.
In PARALLEL mode:
- Never execute more than one task
- Never modify files outside that task's
Files:section without stopping - Never update statuses for other tasks
- Report any cross-scope file need as a blocker
8. Execute Tasks (TDD)
For each task in scope:
A. Update Status
- MANDATORY Read-before-Edit: Use the Read tool to read the plan file immediately before editing it.
- Match the exact indentation and whitespace as shown in the Read output. Copy the status line verbatim from what Read returned.
- If multiple tasks have the same status: include the task heading (
## Task N:) + the status line inold_stringto make the match unique. - If the Edit fails with "String to replace not found", Re-read the plan file, then retry with the current content. This happens if another process modified the file since your last Read.
- Change
Status: pending→Status: in_progressin plan file
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.
- 29d ago Changed · +2 lines 75b55ca0c78a
- 1mo ago Changed · +2 lines d73c40119d5f
- 1mo ago First seen · 179 lines · 25 tokens per session scan A e31f0f7bfdf8
executor is an agent published in the GitHub repository datit309/supergraph (22 stars, last pushed yesterday), licensed MIT. It adds 25 tokens to every session and 1,770 once invoked, about $0.0001 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 2026-08-30.
Other agents, from other repositories
engineer
Implementation specialist. Use for writing production code, refactoring, and TDD-driven feature work.
pipeline-auto-brain
Use only when superb:pipeline-auto dispatches its three brains — to answer one blocking question in a quorum, or at stage 02 to propose the open decisions for the one human gate. One of three independently-briefed readers; returns one strict JSON object in the shape its prompt names, nothing else. Never dispatched by…
pipeline-auto-intent-reader
Use only at superb:pipeline-auto stage 01, to read what the user actually asked for and return it as a strict JSON hypothesis. One of three independent readers. Reads and reports; never designs, never proposes, never chooses a stack.
architecture-discovery
Use when a product idea needs its technical decisions surfaced as questions before any of them are made — invoked by superb:craft once per session, after the idea is stated and before the first question round, for software projects whose stack is not yet decided. Returns candidate questions only; never chooses a stack…
bug-investigator
Use when a bug, regression, or unexpected behaviour needs its root cause traced to specific code before any fix is designed. Investigates only — never edits files. Returns a structured report citing file:line evidence.
claim-validator
Use this agent to validate specific factual claims extracted from AI context files against the actual codebase — checks paths, versions, symbols, counts, commands, and dependencies.