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/redberryproducts/synapse/plan-epicnpx skills add RedberryProducts/synapse --skill plan-epicgit clone --depth 1 https://github.com/RedberryProducts/synapseWrote 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/redberryproducts/synapse/plan-epic)<a href="https://agentmods.dev/skills/redberryproducts/synapse/plan-epic"><img src="https://agentmods.dev/badge/skills/redberryproducts/synapse/plan-epic.svg" alt="Measured on agentmods" 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 | $0.00100 | $0.01606 |
| Opus 5 | $0.00050 | $0.00803 |
| Sonnet 5 | $0.00020 | $0.00321 |
| Haiku 4.5 | $0.00010 | $0.00161 |
Grade A, and why
plan-epic 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 5d 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.
get_screenshot(nodeId) → visual + a URL to curl into screenshots/ (expires fast — download immediately) How it starts
The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Planning a Synapse epic
Epic plans live in plans/epic-NN-name/PLAN.md with a screenshots/ folder alongside. plans/PLAN.md is the roadmap; epic-01-discovery is the reference implementation of this format.
A good epic plan is executable without re-deriving research: every SDK fact verified, every Figma component identified by node id, every config key listed, every AC testable.
Sourcing rules
| Section | Source | Rule |
|---|---|---|
| Goal / scope | GOAL.md + PRD.md | GOAL for user-visible behavior, PRD for the feature's mechanism. Link both. |
| Design | Figma via MCP | Cite node ids, not just screen names. Export a screenshot into screenshots/. |
| Frontend components | Figma components sheet + plans/FRONTEND.md + the current repo | List every component the epic uses, in its layer (elements / components / composed / pages), each marked Done / Create / Adjust. During the MVP we name ours after the Figma component when there is one. |
| Config | PRD "Configuration" + GOAL "Configuration" | List only keys this epic reads. Flag any new key as a PRD change first. |
| Technical approach | PRD feature section, verified against references/laravel/ai |
Never restate the PRD from memory — open the SDK source and confirm. |
| Tests | PRD + ACs | Every AC maps to at least one test. |
Verify, don't assume. The PRD is already SDK-verified, but APIs move. Before writing a technical section, read the actual classes in references/laravel/ai/src. If reality differs from the PRD, stop and reconcile the PRD — don't silently plan against the new finding.
Required sections
# Epic N — Name
**Goal:** one sentence, user-visible.
Delivers PRD [Feature X](...) · GOAL [section](...) · Success Criterion #N.
**Depends on:** ... · **Blocks:** ...
## Design
Screen links (node ids) + local screenshot + a component table:
| Figma component | Node | Variants |
## Frontend components to use
Follow the four layers in plans/FRONTEND.md — one table per layer used.
EVERY row carries a Status: Done | Create | Adjust (see below).
### 1. Elements (resources/js/elements/)
| Element | Status | Figma | Used by | Notes |
### 2. Components (resources/js/components/)
| Component | Status | Figma | Responsibility |
### 3. Composed (resources/js/composed/)
| Component | Status | Figma | Responsibility |
### 4. Pages (resources/js/pages/)
| Page | Status | Responsibility |
### Data layer
| File | Status | Responsibility | ← types, hooks, api client additions
### Styling
Which token/style files change.
## Configuration
| Key | Default | Use here | ← synapse.* keys this epic reads
| Key | Use here | ← host-app keys (ai.*) read but never written
State explicitly whether the epic introduces new config (it should usually not).
## Technical approach
Numbered subsections, each with verified SDK detail and a code sketch where it
removes ambiguity. Call out traps (e.g. "ProviderTool has no name()").
## API
Exact request + response JSON with comments on enum-ish fields.
## Acceptance criteria
Numbered, testable, user-observable. Include auth/gate and both themes.
## Code map
| Area | Path |
## Tests
Feature bullets + Browser bullets + workbench fixtures to add.
## Risks
| Risk | Mitigation |
## Definition of done
ACs verified · `composer check` green · tests added · both themes · dist rebuilt ·
PRD/GOAL updated if a decision changed.
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.
- 5d ago First seen · 123 lines · 100 tokens per session scan A efbe10702fca
plan-epic is a skill published in the GitHub repository RedberryProducts/synapse (22 stars, last pushed 3d ago), licensed MIT. It adds 100 tokens to every session and 1,606 once invoked, about $0.0005 per session on Opus 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
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…