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 skills/odinmb/ops-workflow/executenpx skills add OdinMB/ops-workflow --skill executegit 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 | $0.00029 | $0.01008 |
| Opus 5 | $0.00015 | $0.00504 |
| Sonnet 5 | $0.00006 | $0.00202 |
| Haiku 4.5 | $0.00003 | $0.00101 |
Grade A, and why
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 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Execute the plan at: $ARGUMENTS
Scope: This skill produces research, content, strategy, and specs — not code. If the plan involves code changes, use /implement instead.
Instructions
1. Read the plan
Read the plan file. Understand the objective, steps, and success criteria.
2. Execute
Carry out the plan:
- Do the research, analysis, or writing described in the plan.
- When researching, always cite sources — include URLs, document names, or specific references.
- Store outputs in the appropriate location:
- Research findings →
references/<topic>/ - Work products and deliverables →
artifacts/(or as specified in the plan)
- Research findings →
- If the plan needs to change mid-execution (new information, blocked path), update the plan file and confirm the revised approach with the user before continuing.
Opportunity lifecycle: When researching and qualifying opportunities (grants, partnerships, platforms, etc.):
- Raw idea → backlog item. The item is the task: "research and qualify this."
- After research → reference file gets the findings. Then either:
- Pursue → backlog action item linking to the reference
- Pass → reference entry updated with pass rationale + date, backlog entry removed
3. Review
Before updating state, review the deliverables. In autonomous execution this is the only verification gate — nothing you produce is seen by a human before it lands in the repo's state and knowledge base — so approach it as a skeptic reading someone else's work, not as a rubber-stamp of what you just wrote. A clean pass is fine, but only after you've genuinely tried to find the weak claim, the unsupported assertion, and the inconsistency:
- Fact-check — verify claims against cited sources. Flag unsupported assertions.
- Consistency — check that new artifacts don't contradict existing state files or prior completed plans.
- Completeness — confirm the output covers everything the plan promised. Fill gaps or note them as out-of-scope with justification.
- Quality — check formatting consistency, broken links, and missing references.
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 · 63 lines · 29 tokens per session scan A 3ae4365f6819
execute is a skill published in the GitHub repository OdinMB/ops-workflow (7 stars, last pushed 15d ago), licensed MIT. It adds 29 tokens to every session and 1,008 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 skills, from other repositories
dev-finish
Close out a session — summarise what changed, capture what was learned, and prepare the commit.
dev-full-auto
Hand over a spec and walk away — plans, builds, tests and audits on its own, stopping only at a real blocker.
factory-db-migration
The operational discipline for running a destructive change against a production database — schema migrations, data backfills, one-shot RPCs, historical seed imports. Adjacent to factory-data-layer.md (schema design) and factory-deployment.md (where migrations execute in CI) — this skill is about the runbook around…
people-intel
This skill should be used when the user asks to 'research person', 'person intel', 'people intel', 'who is [person]', 'who created [project]', 'who maintains [package]', 'add person to knowledge graph', 'enrich person note', 'update person note', 'document [person]', 'create person note for [name]'. Researches a…
schema-evolve
This skill should be used when the user asks about 'schema drift', 'schema evolution', 'evolve schema', 'schema sync', 'sync schemas', 'update schema fields', 'schema field frequency', 'missing schema fields', 'unused schema fields', 'schema proposal', 'schema cardinality', 'check schema', 'schema audit', 'schema…
factory-api
API conventions for both server actions and tRPC builds. Covers the decision between them, per-mutation Zod input schemas, central router composition, pagination shape, multi-field search via Drizzle ilike + or(), mutation lifecycle hooks, conditional query enabling, stale-time defaults, error response shape and…