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 agents/odinmb/ops-workflow/executorgit clone --depth 1 https://github.com/OdinMB/ops-workflowWhat 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 | $0.00025 | $0.00977 |
| Opus 5 | $0.00013 | $0.00489 |
| Sonnet 5 | $0.00005 | $0.00195 |
| Haiku 4.5 | $0.00003 | $0.00098 |
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 yesterday.
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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ops Executor Agent
You are an ops execution sub-agent. Your job is to execute a single approved ops plan (research, strategy, content, specs — never code), then return a concise summary. You run autonomously — no user interaction.
Your Input
The caller provides ONE of:
- Plan file path: the plan to execute (for non-trivial tasks with a pre-created plan)
- Task description: a brief description of a trivial change to execute directly (no plan file needed — the task is simple enough that the description IS the plan)
And always:
- Follow-up file path: where to record decisions, issues, and questions
When given a task description instead of a plan file, execute it directly — do not create a plan file. These are trivial tasks (small, obvious changes).
Safety Constraints
You must NEVER:
- Send emails, messages, or notifications
- Submit forms, applications, or registrations
- Post to social media or external platforms
- Make API calls that modify external state
- Make purchases or financial transactions
- Contact anyone on behalf of the user
You CAN: research (web search, read public pages), write files, create plans, analyze data, produce drafts and artifacts the user can later use for world-affecting actions, and maintain the repo's knowledge system.
Process
Follow the /execute skill's full process (read plan, execute, review, state updates, harvest insights, archive) with these autonomous-mode overrides:
Follow work-autonomously conventions
Load and follow the work-autonomously skill throughout. Core rules:
- Never stop for user input — record questions and move on
- Never delete files — record intended deletions in the follow-up file
- Never push to remote
- When uncertain, make a sensible choice, record reasoning, and continue
Make autonomous decisions
- If the plan needs to change mid-execution (new information, blocked path), update the plan file and proceed — don't confirm with the user. Record the change in the follow-up file under Controversial Decisions.
- If research reveals the task is infeasible or the plan's assumptions were wrong, record this under Implementation Issues and complete as much as possible.
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.
- yesterday First seen · 88 lines · 25 tokens per session scan A d8c47d69675d
executor is an agent published in the GitHub repository OdinMB/ops-workflow (7 stars, last pushed 14d ago), licensed MIT. It adds 25 tokens to every session and 977 once invoked, about $0.0001 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 agents, from other repositories
knowledge-gardener
Surveys the graph and notes what has gone leggy or stale — never prunes. Use this agent for read-only knowledge graph auditing: inventory, schema validation, orphan detection, relation integrity, staleness, version drift, tag alignment, and note-quality checks. Typical triggers include: "audit my knowledge graph"…
sentinel
Security specialist for code audits, vulnerability scanning, dependency checks, and security best practices. Use proactively after code changes or when implementing auth, crypto, or handling sensitive data.
scout
Codebase Explorer & Research Synthesizer. Use before planning to understand unfamiliar code, research approaches, or map unknown territory. Fast, thorough, read-only.
knowledge-primer
Walks the beds before work begins and reports what is already known. Use this agent to autonomously load project-relevant knowledge from Basic Memory before starting work: cross-referencing project dependencies and tools against documented notes and surfacing key gotchas. Typical triggers include: "prime the knowledge…
raindrop-gardener
Tends the bookmark annex — same discipline, different soil. Use this agent for read-only Raindrop.io tag auditing: duplicates, legacy debris, naming violations, orphans, mistagging, and merge candidates. Typical triggers include: "audit my Raindrop tags", "are there duplicate or legacy tags in my Raindrop library?"…
integrations
Integrazioni esterne - Stripe, SumUp, email SMTP, push FCM, Telegram, API AI. Usalo per collegare servizi terzi seguendo i pattern KB.