Borrowing it
Nothing to install: this file belongs to Codename-11/SubFrame. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Codename-11/SubFrame/main/.agents/skills/sub-docs/SKILL.mdgit clone --depth 1 https://github.com/Codename-11/SubFrameWrote 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/codename-11/subframe/sub-docs)<a href="https://agentmods.dev/skills/codename-11/subframe/sub-docs"><img src="https://agentmods.dev/badge/skills/codename-11/subframe/sub-docs/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/codename-11/subframe/sub-docs"><img src="https://agentmods.dev/badge/skills/codename-11/subframe/sub-docs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00032 | $0.00714 |
| Opus 5.5 | $0.00013 | $0.00286 |
| Sonnet 5.5 | $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 1mo 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 — 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.
- 1mo ago 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 yesterday), licensed MIT. It adds 32 tokens to every session and 714 once invoked, about $0.0001 per session on Opus 5.5. 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-shape
Shape unsettled product ideas into bounded bets before planning; excludes settled fixes and approved execution.
intuitive-doc
Maintain README.md, ARCHITECTURE.md, STATUS.md, and docs/human/ when they drift or need cleanup.
research
Investigate a bounded question using multiple sources or a cited report; answer single facts and codebase questions directly.
intuitive-reduce-entropy
Find and rank material simplification candidates when the cleanup target or plan risks are unclear.
intuitive-refactor
Execute a selected cleanup seam after its target and scope are known; use reduce-entropy for discovery.
agent-planning-loop
Review unsettled plans with independent scouts when the user requests multi-agent planning or alignment.