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-ipcnpx skills add Codename-11/SubFrame --skill sub-ipcgit 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 | $0.00018 | $0.00769 |
| Opus 5 | $0.00009 | $0.00385 |
| Sonnet 5 | $0.00004 | $0.00154 |
| Haiku 4.5 | $0.00002 | $0.00077 |
Grade A, and why
sub-ipc 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SubFrame IPC Reference Regeneration
Regenerate .subframe/docs-internal/refs/ipc-channels.md from the source of truth: src/shared/ipcChannels.ts.
Dynamic Context
Current channel count:
!node -e "const src=require('fs').readFileSync('src/shared/ipcChannels.ts','utf8'); const m=src.match(/^\s+\w+:\s*'/gm); console.log(m ? m.length + ' channels in IPC constant' : 'Could not count')"
Instructions
Step 1: Read Source
Read src/shared/ipcChannels.ts completely. Extract:
- IPC constant — all channel name constants, grouped by their comment headers (e.g.,
// Terminal,// Workspace) - IPCHandleMap — channels using the
handlepattern (request/response) - IPCSendMap — channels using the
sendpattern (fire-and-forget) - IPCEventMap — channels using the
eventpattern (main→renderer push)
Step 2: Classify Each Channel
For every channel in the IPC constant, determine its pattern:
- If it appears in
IPCHandleMap→handle - If it appears in
IPCSendMap→send - If it appears in
IPCEventMap→event - If it appears in both
IPCSendMapandIPCEventMap→send + event(bidirectional) - If it appears in NONE of the maps →
⚠(untyped/legacy)
Step 3: Write Reference Doc
Write .subframe/docs-internal/refs/ipc-channels.md with this structure:
# IPC Channel Reference
**Source of truth:** `src/shared/ipcChannels.ts`
All channels are typed. Three communication patterns are used:
| Pattern | Direction | Usage |
|---------|-----------|-------|
| `ipcMain.handle` / `ipcRenderer.invoke` | Renderer → Main (request/response) | Data fetching, mutations |
| `ipcRenderer.send` / `ipcMain.on` | Renderer → Main (fire-and-forget) | Commands, notifications |
| `webContents.send` / `ipcRenderer.on` | Main → Renderer (push events) | Data updates, state changes |
Channels marked ⚠ are defined in the `IPC` constant but not yet in `IPCHandleMap`, `IPCSendMap`, or `IPCEventMap` type maps.
---
## Channels by Domain
### {Domain} ({N} channels)
| Channel | Pattern | Purpose |
|---------|---------|---------|
| `CHANNEL_NAME` | pattern | Brief purpose |
...
---
**Total: {N} channels** ({H} handle, {S} send, {E} event, {U} untyped/legacy)
*Regenerated from `ipcChannels.ts` — keep this reference in sync when adding/removing channels.*
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 · 85 lines · 18 tokens per session scan A af3b3d47927b
sub-ipc is a skill published in the GitHub repository Codename-11/SubFrame (10 stars, last pushed 8d ago), licensed MIT. It adds 18 tokens to every session and 769 once invoked, about $0.0001 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…