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-docsnpx skills add Codename-11/SubFrame --skill sub-docsgit 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 | $0.00714 |
| Opus 5 | $0.00016 | $0.00357 |
| Sonnet 5 | $0.00006 | $0.00143 |
| Haiku 4.5 | $0.00003 | $0.00071 |
Grade A, and why
sub-docs 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SubFrame Documentation Sync
After significant feature work, synchronize all SubFrame documentation references. This skill automates the "Before Ending Work" checklist.
Dynamic Context
Current version:
!node -e "console.log(require('./package.json').version)" 2>/dev/null || echo "unknown"
Recent commits (last 10):
!git log --oneline --no-decorate -10 2>/dev/null || echo "No git history"
Files changed (unstaged + staged):
!git diff --name-only HEAD 2>/dev/null | head -30
Instructions
Argument: $ARGUMENTS
The argument should describe what feature/changes were made. If empty, infer from recent git changes.
Step 1: Identify What Changed
Read the recent changes (git diff, argument context) and categorize:
- New source modules → update AGENTS.md module lists (if applicable)
- New components → update AGENTS.md component lists (if applicable)
- Architecture decisions → add to
.subframe/PROJECT_NOTES.mdSession Notes - User-facing features → add to
.subframe/docs-internal/changelog.mdunder [Unreleased]
Step 2: Update AGENTS.md
Read AGENTS.md and update only the sections that need changes. If AGENTS.md has module/component lists, add new entries. Preserve existing formatting and ordering.
Rules:
- Only add genuinely new entries — don't duplicate
- Keep formatting consistent with existing entries
- Don't modify user-written content outside SubFrame-managed sections
Step 3: Update Changelog
Read .subframe/docs-internal/changelog.md and add entries under ## [Unreleased].
Format: Follow the existing changelog style:
- Group under
### Added,### Changed,### Fixed,### Removed - Bold feature name, em-dash, brief description
- Sub-bullets for implementation details
Step 4: Update PROJECT_NOTES (if architecture decision)
If the work involved an architecture decision worth preserving, add a session note to .subframe/PROJECT_NOTES.md under ## Session Notes.
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 · 93 lines · 32 tokens per session scan A a54fcd2fd53b
sub-docs 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 714 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…
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…
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…