Borrowing it
Nothing to install: this file belongs to fokkerone/superspecs. 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/fokkerone/superspecs/main/.skills/wiki-capture/SKILL.mdgit clone --depth 1 https://github.com/fokkerone/superspecsWrote 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/fokkerone/superspecs/wiki-capture)<a href="https://agentmods.dev/skills/fokkerone/superspecs/wiki-capture"><img src="https://agentmods.dev/badge/skills/fokkerone/superspecs/wiki-capture/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/fokkerone/superspecs/wiki-capture"><img src="https://agentmods.dev/badge/skills/fokkerone/superspecs/wiki-capture.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 | $0.00074 | $0.00884 |
| Opus 5 | $0.00037 | $0.00442 |
| Sonnet 5 | $0.00015 | $0.00177 |
| Haiku 4.5 | $0.00007 | $0.00088 |
Grade A, and why
wiki-capture 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 9d 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: wiki-capture
You are capturing knowledge from the current session before it disappears.
The context window is ephemeral. This skill saves what's worth keeping — decisions made, bugs fixed, patterns discovered, gotchas hit — directly to the wiki or to raw/ for later ingest.
Use this mid-session when something important happened that shouldn't be lost.
Modes
--quick (default)
Stage a structured draft to superspec/wiki/raw/capture-<YYYY-MM-DD-HH-MM>.md.
Fast: no subagent, no manifest update, no cross-linking.
The next /wiki or /wiki-ingest run will promote the raw file to proper pages.
--full
Distill directly to proper wiki pages. Follows the full ingest process from verify-wiki.
Use when the session produced significant, self-contained knowledge worth filing immediately.
Steps
1. Scan the current session
Review what happened in this session. Extract the following (drop noise):
Worth capturing:
- Decisions made (what was chosen, why, what was traded away)
- Bugs found and fixed (what the bug was, root cause, fix)
- Patterns established or discovered
- Gotchas — things that took longer than expected
- Interface or contract changes
- Open questions that arose but weren't resolved
Drop:
- Step-by-step implementation details already in code
- Routine task execution
- Anything that's obvious from reading the code
2. Quick mode — stage to raw/
Create superspec/wiki/raw/capture-<YYYY-MM-DD-HH-MM>.md:
---
capture_date: <YYYY-MM-DD HH:MM>
session_context: <brief description of what this session was about>
promote: true
---
# Session Capture: <YYYY-MM-DD>
## Decisions
### <Decision>
**Chose:** <X>
**Over:** <Y>
**Because:** <reason>
## Bugs Fixed
### <Bug title>
**Symptom:** <what it looked like>
**Root cause:** <why it happened>
**Fix:** <what resolved it>
**Gotcha:** <anything surprising>
## Patterns
### <Pattern name>
<What the pattern is and when to use it>
## Open Questions
- [ ] <Question that came up but wasn't resolved>
## Files touched
- `<path/to/file>` — <what changed and why>
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.
- 9d ago First seen · 137 lines · 74 tokens per session scan A 83254fb2b73d
wiki-capture is a skill published in the GitHub repository fokkerone/superspecs (4 stars, last pushed 2mo ago), licensed MIT. It adds 74 tokens to every session and 884 once invoked, about $0.0004 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.
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
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…