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 skills add cmdr-chara/codex-toolkit --skill delegate-with-mission-cardsgit clone --depth 1 https://github.com/cmdr-chara/codex-toolkitWrote 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/skills/cmdr-chara/codex-toolkit/delegate-with-mission-cards)<a href="https://agentmods.dev/skills/cmdr-chara/codex-toolkit/delegate-with-mission-cards"><img src="https://agentmods.dev/badge/skills/cmdr-chara/codex-toolkit/delegate-with-mission-cards.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 5.1 | $0.00077 | $0.00961 |
| Opus 5 | $0.00039 | $0.00481 |
| Sonnet 5 | $0.00015 | $0.00192 |
| Haiku 4.5 | $0.00008 | $0.00096 |
Grade A, and why
delegate-with-mission-cards 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 8d 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.
How it starts
The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mission Control
Keep the parent on the critical path. Delegate execution, not accountability. The parent owns decomposition, sequencing, product judgment, integration, validation, and the final answer.
Delegation gate
Delegate only when the outcome and acceptance criteria are concrete, inputs are stable, scope is precise, execution is independent, evidence can verify the result, and delegation saves more time or context than briefing and review consume.
Keep work in the parent when it is small, tightly coupled, destructive, primarily a product decision, dependent on unavailable credentials, or too ambiguous for a stop condition.
Mission ledger
Record candidates before spawning:
ID | objective | role | dependencies | read scope | write scope | acceptance evidence
Mark each Ready, Blocked, or Parent-owned. Launch only Ready missions and run dependent work in waves.
Choose the lightest capable role
| Role | Use for |
|---|---|
pathfinder-reader |
Fast reconnaissance, files and symbols, codebase maps, and narrow facts |
investigator-reader |
Debugging, behavior tracing, root causes, reviews, and option comparison |
sentinel-reader |
Security, auth, privacy, migrations, architecture, public APIs, and subtle high-consequence analysis |
patcher-writer |
Tiny, isolated, reversible edits with an obvious diff and fast validation |
builder-writer |
Standard implementation, tests, fixes, contained refactors, docs, and configuration |
architect-writer |
High-risk migrations, architecture changes, security hardening, and failure-sensitive work |
Escalate for ambiguity, blast radius, irreversibility, hidden coupling, or difficult validation. Never escalate merely because work contains many repetitive items.
Model tiers
Use Luna Max for the four general roles: pathfinder-reader, patcher-writer, investigator-reader, and builder-writer. Escalate high-risk read-only review to sentinel-reader on Sol High. Reserve Sol Max for architect-writer, where irreversible migrations, architectural risk, security hardening, or failure-sensitive integration justify the highest tier. Do not escalate merely because a mission is long, repetitive, or important.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 8d ago First seen · 98 lines · 77 tokens per session scan A 40d8e9e9ea50
delegate-with-mission-cards is a skill published in the GitHub repository cmdr-chara/codex-toolkit (2 stars, last pushed 10d ago), licensed MIT. It adds 77 tokens to every session and 961 once invoked, about $0.0004 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
boss-advanced
Advanced Boss orchestration patterns — Agent Teams leadership, 6-section delegation template, Skill vs Agent conflict resolution, Guardian pattern, and AI-slop detection.
gstack-sprint
3-Phase Sprint workflow — design → execute → review with user interaction at decision points.
boss-briefing
Vault health check — workflow pattern analysis, profile sync, session gap recovery, persona rule proposals.
briefing-vault
Initialize, manage, and search the per-project .briefing/ vault. Obsidian-compatible persistent knowledge base.
dynamic-workflows
Use for bounded native Codex multi-agent orchestration when a task has at least two independent workstreams or independent verification would materially improve confidence: broad or high-risk multi-step work, audits, migrations, multi-area review-and-fix, adversarial verification, cross-checked research, or explicit…
code-review-excellence
This skill should be used when the user asks to review a diff or pull request, write review comments, audit code quality, establish review standards, or improve how a team performs code review.