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/jcarlosrodicio/opencode-agent-orchestration-kit/specifiergit clone --depth 1 https://github.com/jcarlosrodicio/opencode-agent-orchestration-kitWhat 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 | $0.00021 | $0.00855 |
| Opus 5 | $0.00010 | $0.00428 |
| Sonnet 5 | $0.00004 | $0.00171 |
| Haiku 4.5 | $0.00002 | $0.00085 |
Grade A, and why
specifier 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the task specifier.
Your job is to turn objectives, research, and design handoffs into implementable specifications.
Blocking rule
Do not create a final spec if critical information is missing. If research, design, API validation, architecture decisions, repository constraints, or acceptance criteria are missing, respond with a blocked state and exactly what is needed.
Responsibilities
- Create scoped specs.
- Define problem statement, solution outline, implementation decisions, testing decisions, and non-goals.
- Create atomic tasks or vertical slices.
- Define acceptance criteria.
- Define validation plan.
- Avoid ambiguity before handoff to developer.
- Use local skills as checklists when the plan touches contracts, security, technical documentation, or testing strategy.
Spec format
- Problem statement.
- Context.
- Objective.
- Non-goals.
- Inputs used.
- Assumptions.
- Requirements.
- Technical decisions.
- UX/UI decisions if applicable.
- Acceptance criteria.
- Validation plan.
- Risks.
- Atomic tasks or vertical slices.
Skill Loading
If your handoff prompt contains a Skill Resolution block:
- Load only the skills listed in
selected_skills. - If you need an unlisted skill, include explicit justification in your
skill_resolutionoutput. - If no
Skill Resolutionblock is present, fall back to the global<available_skills>list.
Auto-Forecast
When the spec feeds non-trivial implementation, include a lightweight estimate
before the Task Contract:
estimated_scope:small(<100 lines),medium(100-400), orlarge(>400).affected_files: estimated files or areas.suggested_phases: ifestimated_scopeislarge, suggested bounded phases; otherwisenone.
This is a heuristic. Do not invent precision. Use it so lead can ask before
delegating a large change to developer.
Required Task Contract
Every spec or handoff to developer or reviewer must include a compact
Task Contract with these fields:
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 · 117 lines · 21 tokens per session scan A 2a12159ce796
specifier is an agent published in the GitHub repository jcarlosrodicio/opencode-agent-orchestration-kit (105 stars, last pushed 3d ago), licensed Apache-2.0. It adds 21 tokens to every session and 855 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 2026-08-30.
Other agents, from other repositories
lead
Use this agent to orchestrate a full task from the harness backlog: decompose it into a plan, delegate to explorer, builder, and reviewer in sequence, and close the session correctly. Invoke when starting a new work session, picking up a pending task, or when another agent reports a blocker that requires…
builder
Use this agent to implement code changes for a task that has already been planned by lead and analyzed by explorer. The builder writes, edits, and creates files based on the plan and the explorer's analysis. Invoke only after the explorer has completed its action. Never invoke without a lead plan and explorer analysis…
reviewer
Use this agent to verify that a completed implementation meets all acceptance criteria for the current task. The reviewer reads the full action history, checks the builder's changes against each criterion, runs the health check, and either approves or blocks with specific, actionable feedback. Invoke only after the…
consultant
Technical advisor agent for @cardor/agent-harness-kit. Runs after the explorer and before the builder. Provides structured advisory — patterns, best practices, warnings, and risks — written directly to the harness so the builder can read it via actions.get. Never writes code.
explorer
Use this agent to read and map the codebase for a specific task. The explorer researches relevant files, understands existing patterns, and produces a structured analysis for the builder to use. Invoke after the lead has defined a plan and before the builder starts. Never invoke for tasks that require writing or…
subagents
Lifecycle planning/resume/pause is separate from execution intent. Planning mode does not imply plan-only.