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 commands/yeachan-heo/gajae-code/delegate_plangit clone --depth 1 https://github.com/Yeachan-Heo/gajae-codeWrote 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/commands/yeachan-heo/gajae-code/delegate_plan)<a href="https://agentmods.dev/commands/yeachan-heo/gajae-code/delegate_plan"><img src="https://agentmods.dev/badge/commands/yeachan-heo/gajae-code/delegate_plan.svg" alt="Measured on agentmods" 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 | $0.00022 | $0.00276 |
| Opus 5 | $0.00011 | $0.00138 |
| Sonnet 5 | $0.00004 | $0.00055 |
| Haiku 4.5 | $0.00002 | $0.00028 |
Grade A, and why
plan 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 4d 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.
This is a copy
91% identical to execute — 8 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Call the gjc_delegate_plan coordinator MCP tool to delegate this work to gajae-code.
- Pass the current project directory as
cwd. - Pass the user's request as
task. - Only set
allow_mutation: trueafter the user explicitly approves changes AND the coordinator server was started with thesessionsmutation class enabled. Delegation is read-only until both conditions hold.
GJC starts a session and runs /skill:ralplan to completion, returning a
durable turn_id, status, and artifact references. Poll with
gjc_coordinator_await_turn or gjc_coordinator_watch_events.
Codex resume bridge correlation: after registering an app-server handoff with
gjc_coordinator_register_codex_handoff, pass the same session_id as
codex_host_session_id on delegate calls so the new GJC session auto-binds to
the Codex thread for wake-on-completion and questions. Acknowledge durable wakes
by wake_key with gjc_coordinator_ack_codex_handoff; heartbeats are unsupported
(automation_update_unavailable), so delivery is event-driven with startup drain.
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.
- 4d ago First seen · 23 lines · 22 tokens per session scan A 403da8a36f61
plan is a command published in the GitHub repository Yeachan-Heo/gajae-code (2,691 stars, last pushed 2d ago), licensed MIT. It adds 22 tokens to every session and 276 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 91% identical to execute, differing in 8 lines, and is treated as a copy.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.