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/codename-11/subframe/sub-tasksnpx skills add Codename-11/SubFrame --skill sub-tasksgit clone --depth 1 https://github.com/Codename-11/SubFrameWhat 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 | $0.00032 | $0.00776 |
| Opus 5 | $0.00016 | $0.00388 |
| Sonnet 5 | $0.00006 | $0.00155 |
| Haiku 4.5 | $0.00003 | $0.00078 |
Grade A, and why
sub-tasks 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 2d 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SubFrame Sub-Tasks
Manage the project's Sub-Task system. Sub-Tasks are SubFrame's project task tracking stored as individual markdown files in .subframe/tasks/.
Dynamic Context
Current task index:
!cat .subframe/tasks.json 2>/dev/null || echo "No tasks.json found"
Instructions
Argument: $ARGUMENTS
Task File Format
Each task is a markdown file in .subframe/tasks/ with YAML frontmatter:
---
id: task-abc123
title: My task title
status: pending
priority: medium
category: feature
description: What needs to be done
userRequest: The user's original words
acceptanceCriteria: How to verify completion
blockedBy: []
blocks: []
createdAt: 2024-01-01T00:00:00.000Z
updatedAt: 2024-01-01T00:00:00.000Z
completedAt: null
---
## Notes
Session notes go here.
## Steps
- [ ] Step one
- [x] Step two (completed)
Operations
List tasks
Read .subframe/tasks.json for the index overview, or glob .subframe/tasks/*.md and read frontmatter.
Get task details
Read the specific .subframe/tasks/<id>.md file.
Start a task (pending → in_progress)
Edit the task's frontmatter: set status: in_progress and update updatedAt.
Complete a task
Edit the task's frontmatter: set status: completed, set completedAt to current ISO timestamp, update updatedAt.
Add a new task
Create a new .subframe/tasks/<id>.md file with:
- Generate id:
task-+ 8 random alphanumeric chars - Set
status: pending,createdAtandupdatedAtto current ISO timestamp completedAt: null- Include all required fields in frontmatter
Update a task
Edit the frontmatter fields as needed. Always update updatedAt.
Archive completed tasks
Move completed .md files to .subframe/tasks/archive/YYYY/ (create directory if needed).
After Any Write Operation
Regenerate the .subframe/tasks.json index by reading all .subframe/tasks/*.md files (excluding archive/) and building the JSON structure with tasks grouped by status (pending, inProgress, completed).
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.
- 2d ago First seen · 108 lines · 32 tokens per session scan A f62f630dc1a0
sub-tasks is a skill published in the GitHub repository Codename-11/SubFrame (10 stars, last pushed 8d ago), licensed MIT. It adds 32 tokens to every session and 776 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 2026-08-31.
Other skills, from other repositories
intuitive-tests
Use this skill whenever the user asks about unit test best practices, test organization, flat test suites, redundant tests, test refactors, pytest/JUnit/Jest/xUnit layout, test taxonomy, flaky tests, coverage quality, fixtures, mocks, parametrization, pruning existing UTs, or "which tests are worth keeping." It…
intuitive-flow
Stable execution/change router after an approved plan, preflight contract, or tiny concrete task. Refactor-shaped work delegates to intuitive-refactor, and durable work runs through staged planning, review, GSD handoff, implementation, cleanup, and verification while keeping plan ledgers and active capsules compact by…
intuitive-preflight
Turn a vague task, plan, issue, or "LGTM/go ahead" request into an approval-ready preflight contract before implementation starts. Use when the user wants prompt preflight, clearer scope, non-goals, context package, acceptance criteria, definition of done, verification, stop gates, the exact execution command, or…
intuitive-squash
Squash local GSD or agent-generated commit history into a clean, reviewable story while preserving important fixes. Use when the user asks to squash commits, clean git history, compress phase commits, prepare a branch before PR, compare aggressive vs moderate squash options, or preserve hotfix/security commits during…
multica-goal-tracker
Track goal-driven Multica issues. Use when a user creates or maintains Multica issues by pasting a /goal prompt, wants Codex to summarize that goal into a concise issue purpose, append a normalized goal-start comment, record completion evidence from real Multica execution run messages or a supplied session transcript…
cross-review
Challenge an existing agent proposal through a small bounded set of independent review perspectives, then judge the findings into one simpler or more defensible recommendation. Use immediately after an agent proposes a solution when the user asks whether there is a simpler approach, wants a second opinion or other…