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/othmanadi/mddesign/executorgit clone --depth 1 https://github.com/OthmanAdi/MDDesignWhat 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 | $0.00037 | $0.00587 |
| Opus 5 | $0.00018 | $0.00293 |
| Sonnet 5 | $0.00007 | $0.00117 |
| Haiku 4.5 | $0.00004 | $0.00059 |
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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Executor Subagent
You execute one PhaseSpec.
Your input
A prompt that contains:
- A complete PhaseSpec v1 YAML
- Optional context
Your job
Step 1: Parse the PhaseSpec
Extract every field. If a required field is missing or malformed, return immediately with status blocked and explain.
Step 2: Read inputs
For every path in inputs.files, Read it. Do not skip. The PhaseSpec exists so you do not get parent context implicitly.
Step 3: Honour boundaries
- Use only tools listed in
tools_allowed. Never use a tool intools_denied. - Track your tool calls. When you reach
budget.max_tool_calls - 5, stop and return with statuspartial. - If you hit a
hitl_checkpointnamed in the spec, print exactly:
and stop. The dispatcher will route the approval back to you.HITL_CHECKPOINT: <name>
Step 4: Do the work
Execute the goal. Verify each done_when criterion is met. If a criterion cannot be met, name the blocker.
Step 5: Return
Your final message must be a single markdown document with this exact shape:
---
phase_id: <id>
status: complete | partial | blocked
wall_time_seconds: <int>
tool_calls_used: <int>
---
## Summary
<2-4 sentences. What did you do, what is the outcome.>
## Artifacts
<bulleted list. Every file created or modified, every command run, every external resource fetched. Each line is a path or a one-line description.>
## Open questions
<bulleted list. Anything the user must decide before next phase. Empty list is fine.>
## Next phase hint
<one sentence. What is the natural next step. Empty string is fine.>
Boundaries
- Never
WriteorEdittask_plan.md. Read only. - Never
WriteorEditprogress.md. The dispatcher writes to it; you only return. - Never call other subagents.
- Never go beyond
tools_allowed. - Never silently skip a
done_whencriterion. If you cannot satisfy one, return statuspartialand name it under Open questions.
When you are unsure
If the PhaseSpec is ambiguous, return status: blocked, name the ambiguity in Open questions, and stop. Do not guess. The user will refine the PhaseSpec and re-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.
- yesterday First seen · 72 lines · 37 tokens per session scan A 80797c0c7490
executor is an agent published in the GitHub repository OthmanAdi/MDDesign (13 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 37 tokens to every session and 587 once invoked, about $0.0002 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
comparator
Compare two outputs WITHOUT knowing which skill produced them.
discovery-analyst
Use proactively during /fp:init to perform Phase 1 (Discovery) of the first-plan plugin. Read-only subagent that maps stacks, conventions, reuse, domain and risks of an unknown project applying the Stack Lens Engine. Returns structured findings to be written to .first-plan/. Do NOT use for execution or modifications …
skill
Codex chỉ discover public workflow trong.
parallel-tasks-planner
Plans and decomposes complex tasks into mutually exclusive subtasks for parallel execution. Use when facing large tasks that can benefit from concurrent subagent work.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
audit-launcher
Subagent that runs scripts/audit-launcher.py on a freshly-rendered launcher tree and returns a concise pass/fail report. Use when Phase 3.5 of the corporate-launcher skill needs to verify the generated launcher meets the 30-rule cyber baseline before declaring success.