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 implicit-labs/autosymph --skill autoplangit clone --depth 1 https://github.com/implicit-labs/autosymphWrote 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/implicit-labs/autosymph/autoplan)<a href="https://agentmods.dev/skills/implicit-labs/autosymph/autoplan"><img src="https://agentmods.dev/badge/skills/implicit-labs/autosymph/autoplan/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/implicit-labs/autosymph/autoplan"><img src="https://agentmods.dev/badge/skills/implicit-labs/autosymph/autoplan.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00050 | $0.06821 |
| Opus 5.5 | $0.00020 | $0.02728 |
| Sonnet 5.5 | $0.00010 | $0.01364 |
| Haiku 4.5 | $0.00005 | $0.00682 |
Grade A, and why
autoplan scanned grade A with 1 finding 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 2mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
If the description or any comment contains image attachments (Linear renders them as `` markdown), pull them in with `mcp__linear__extract_images` (pass the markdown). Do NOT `curl` How it starts
The opening of the file, as written. The whole thing — 590 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan Phase Orchestrator
Research, Interview, Premortem, PRD, (optional) cross-harness review.
Input: $ARGUMENTS — Linear issue ID (like "ISSUE-123") or feature description, plus optional flags.
Skills used: codebase-explore, documentation-explore, web-research (optional)
Flags: Parsed from $ARGUMENTS. Flags can appear anywhere in the arguments.
| Flag | Variable | Default | Effect |
|---|---|---|---|
claude-codex |
harness preset | default | Claude plans, Codex answers automated questions, Codex reviews first |
codex-claude |
harness preset | none | Codex plans, Claude answers automated questions, Claude reviews first |
codex |
harness preset | none | Short alias for codex-claude; /autoplan codex ... flips the harnesses |
--auto |
IS_AUTO |
false |
Configured question harness answers interview questions instead of user |
--codex-review |
IS_CODEX_REVIEW |
false |
Enables review loop after drafting (review harness first; opposite harness fallback if unavailable) |
--skip-planning-transition |
IS_SKIP_PLANNING_TRANSITION |
false |
Skips Step-1 move to Linear "Planning". Use when caller is autosymph-autoplan, where the issue already lives in "Autoplan" and stays there until Step 7.7 moves it to "Ready". |
| `--planner-harness=claude | codex` | PLANNER_HARNESS |
preset default (claude) |
| `--question-harness=codex | claude` | QUESTION_HARNESS |
preset default (codex) |
| `--review-harness=codex | claude` | REVIEW_HARNESS |
preset default (codex) |
--codex-model=<id> |
CODEX_MODEL |
gpt-5.4 |
Model passed to codex exec -m <id>. If gpt-5.4 is deprecated, override here. |
--claude-review-model=<id> |
CLAUDE_REVIEW_MODEL |
claude-opus-4-7 |
Model used by the Claude-as-reviewer fallback Agent when Codex is unavailable. |
Mode matrix:
| Flags | Interview | Review | Use case |
|---|---|---|---|
| (none) | User answers | No review | Quick planning with user |
--auto |
Preset question harness answers | No review | Headless autoplan, no human |
--codex-review |
User answers | Configured review harness loop | Formal planning with user |
--auto --codex-review |
Preset question harness answers | Configured review harness loop | Full autonomous planning |
codex --auto --codex-review |
Claude answers | Claude loop over Codex plan | Full autonomous planning with flipped harnesses |
--auto --codex-review --skip-planning-transition |
Preset question harness answers | Configured review harness loop | Headless under autosymph "Autoplan" Linear state (ISSUE-123) |
Pipeline context: See WORKFLOW.md for the full Triage → Done pipeline.
Permissions: See PERMISSIONS.md for the allow-list needed to run autonomously.
What ships with it
3 files 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.
- 2mo ago First seen · 590 lines · 50 tokens per session scan A 64f7a3bcb0f5
autoplan is a skill published in the GitHub repository implicit-labs/autosymph (5 stars, last pushed 2mo ago), licensed MIT. It adds 50 tokens to every session and 6,821 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
component-fixtures
Use when creating or updating component fixtures for screenshot testing or their shared infrastructure, or when designing UI components to be fixture-friendly. Covers fixture file structure, theming, service setup, CSS scoping, async rendering, validation, and common pitfalls.