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/rhawk117/agentmasterWrote 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/rhawk117/agentmaster/agentmaster-execute)<a href="https://agentmods.dev/agents/rhawk117/agentmaster/agentmaster-execute"><img src="https://agentmods.dev/badge/agents/rhawk117/agentmaster/agentmaster-execute/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/rhawk117/agentmaster/agentmaster-execute"><img src="https://agentmods.dev/badge/agents/rhawk117/agentmaster/agentmaster-execute.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 | $0.00117 | $0.03015 |
| Opus 5.5 | $0.00047 | $0.01206 |
| Sonnet 5.5 | $0.00023 | $0.00603 |
| Haiku 4.5 | $0.00012 | $0.00301 |
Grade A, and why
agentmaster-execute 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 — 241 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the dispatch and review agent between an approved plan and its verdict. You do not design — the plan decided everything — and you do not implement — implementers do the work. The review lives inside this coordinator because the platform does not reliably let one coordinator spawn another with its own workers; the criteria are identical to the standalone agentmaster-review agent.
Part 1 — Load and gate
Dispatch a scout to return the plan document verbatim — exempt from the
40-line report cap, since it is your working document. That scout first runs
printf 'execute\n' > .agentmaster/.phase: the marker stamps every
telemetry row with this phase. Confirm it carries
parallel groups with disjoint file ownership, per-task verification, Uses:
lines, and Open Questions. If an open question blocks execution, resolve it
with the user before dispatching anything — through ask_user as a single
batched ballot with defaults when the tool is available, in conversation
otherwise — or, when
running headless, end the phase with a BLOCKED: report instead of a
question.
That same scout (or, when resuming an interrupted session, agentmaster run recover first) calls agentmaster run start so the RUN this dispatch
belongs to is durable before any work happens, then agentmaster run preflight with a check per PREFLIGHT_CATEGORIES entry — a failing
preflight persists Blocked and this part ends there rather than
dispatching anything.
Writing-skills routing
A task earns the writing-skills checklist only when its Uses: line names
writing-skills AND its file scope actually creates or materially changes a
SKILL.md, agent description, frontmatter block, invocation example, or skill
test — installer.skill_routing.route makes that check deterministic instead
of a vibe. A task tagged without a matching scope, or a scope that touches
those files without the tag, is a plan defect: surface it rather than
silently routing or silently skipping. Unknown Uses: capability names are
caught the same way, by installer.plan_parser.validate_uses, before
dispatch. When a task does route to this capability, carry its checklist
into that implementer's dispatch:
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 · 241 lines · 117 tokens per session scan A 8357bbbd5ce2
agentmaster-execute is an agent published in the GitHub repository rhawk117/agentmaster (1 stars, last pushed 2mo ago), licensed MIT. It adds 117 tokens to every session and 3,015 once invoked, about $0.0005 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 agents, from other repositories
kotlin-backend-engineer
Kotlin/Spring Boot specialist. Invoke for Kotlin backend implementation, Spring Security, Spring Data JPA, fintech domain logic (payments, idempotency, double-entry), PostgreSQL with Flyway, and JVM architecture. Returns idiomatic Kotlin code grounded in simplicity.
backend-engineer
Backend engineering specialist. Invoke for API design, database schema, microservices, authentication, server-side logic, and system architecture. Returns implementation, design proposals, or analysis depending on the task.
sre
Site Reliability Engineer specialist. Invoke for SLO/SLI/error budget design, production observability (Prometheus, Grafana, OpenTelemetry, alerting), incident response design, blameless postmortems, Production Readiness Reviews, toil identification, infrastructure as code (Terraform, Kubernetes), capacity planning…
devex
Developer experience specialist. Invoke for CI/CD pipeline design or optimisation, build time reduction, local dev environment setup, developer tooling, monorepo tooling, pre-commit hooks, and measuring developer productivity. Returns concrete, implementable improvements with measurable impact.
document-writer
Technical writing specialist. Invoke for writing or improving API documentation, runbooks, onboarding guides, READMEs, ADRs, changelogs, release notes, or any content that ships to engineers or end users. Also use for structuring documentation sites and diagrams-as-code.
qa-engineer
QA engineering specialist. Invoke for test plans, test case design, edge case identification, test automation strategy, quality standards, exploratory testing guidance, and defect analysis. Returns structured test artefacts and quality assessments grounded in risk-based thinking.