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/fragcap/plugin/capsule-knowledgenpx skills add fragcap/plugin --skill capsule-knowledgegit clone --depth 1 https://github.com/fragcap/pluginWhat 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 | $0.00027 | $0.01045 |
| Opus 5 | $0.00014 | $0.00522 |
| Sonnet 5 | $0.00005 | $0.00209 |
| Haiku 4.5 | $0.00003 | $0.00104 |
Grade A, and why
capsule-knowledge 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
FragCap Capsule Knowledge
The FragCap plugin is available in this session.
When to Proactively Search Capsules
Trigger a /fragcap:search when the user's message implies they want to know about others' experiences. This includes (but is not limited to):
- "has anyone else encountered this"
- "has anyone had the same experience"
- "how did others solve this"
- "anyone with a similar experience"
- "am I the only one hitting this"
- "has anyone hit this pitfall before"
- Any phrasing — in any language — that asks whether other people have faced, solved, or documented a similar problem
When triggered, extract the core technical problem from the conversation context and use it as the search query for /fragcap:search. Present the results naturally — e.g., "I found some capsules from other developers who hit similar issues."
When to Suggest Creating a Capsule
After the user resolves a non-trivial problem, you may suggest (not auto-create) drafting a capsule if the solution meets the quality criteria below. Never push without the user's explicit approval.
⚠️ Language Requirement: All capsules MUST be written in English — including problem, solution, pitfalls, attempts, tags, and update notes. Even if the user's conversation is in another language, always generate and push capsule content in English.
Capsule Format
Each capsule is a SKILL.md file — a markdown document with YAML frontmatter that Claude Code can load directly as a skill. Example:
---
id: pgbouncer-pool-202604-a1b2c3d4
description: "Connection pool exhaustion under load with PgBouncer"
tags: ["postgres", "pgbouncer", "connection-pool"]
status: resolved
visibility: anonymous
author: "gh:anonymous-1368de02"
created_at: 2026-04-04T12:00:00.000Z
updated_at: 2026-04-04T12:00:00.000Z
---
# Pgbouncer
## When to Activate
Use this capsule when encountering: Connection pool exhaustion under load with PgBouncer
## Problem
Connection pool exhaustion under load with PgBouncer in production.
## What Does NOT Work
- **Increased pool_size to 200** — Delayed but didn't fix
- **Switched to transaction pooling mode** — Broke prepared statements
## Pitfalls
- PgBouncer silently drops idle connections after server_idle_timeout
## Fix
Set server_idle_timeout=0 and use client-side keepalive instead.
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 · 112 lines · 27 tokens per session scan A 77801a0527f2
capsule-knowledge is a skill published in the GitHub repository fragcap/plugin (2 stars, last pushed 5mo ago), licensed MIT. It adds 27 tokens to every session and 1,045 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
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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
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…