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/rakovi4/continue-framework/docnpx skills add rakovi4/continue-framework --skill docgit clone --depth 1 https://github.com/rakovi4/continue-frameworkWhat 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 | $0.00071 | $0.00848 |
| Opus 5 | $0.00036 | $0.00424 |
| Sonnet 5 | $0.00014 | $0.00170 |
| Haiku 4.5 | $0.00007 | $0.00085 |
Grade A, and why
doc 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/doc - Document Findings
Capture knowledge from a session into a well-structured document under ProductSpecification/, with bidirectional cross-references to related specs, stories, and tasks.
Why This Exists
Research, API discoveries, and architectural findings get lost across conversations. This skill ensures knowledge is captured once, in one canonical location, with links from every document that needs it — so future sessions find the information without re-discovering it.
Usage
/doc # Interactive — asks what to document
/doc "task ordering strategy" # Topic hint
Workflow
Round 1: What and Where
Gather from user:
-
What are we documenting? Summarize the findings in 1-2 sentences. If the current conversation already contains research/findings, extract the summary automatically and confirm with the user.
-
Where should it live? Propose a location based on the topic:
- Existing folder (e.g.,
api-reference/) → add a new.mdfile or append to existing - New folder under
ProductSpecification/→ create{topic-slug}/README.md - Inside a task folder (e.g.,
tasks/35-bug-.../research.md) → already scoped
Decision aid: If the findings are specific to one task/story, keep them in that folder. If they're reusable across multiple stories or tasks, create a shared location.
- Existing folder (e.g.,
-
Filename: Propose based on content (e.g.,
research.md,README.md,{topic}.md). Confirm with user.
Round 2: Cross-References
Identify automatically, confirm with user:
-
What should reference this doc? (inbound links)
- Search for related story
endpoints.mdfiles, taskspec.mdfiles, andCLAUDE.mdthat would benefit from a link to this document. - Use
Grepto find files mentioning the key concepts being documented. - Propose specific files and the line/section where the link should be added.
- Search for related story
-
What should this doc reference? (outbound links)
- Scan the conversation for source materials: story interviews, task specs, external URLs, code files.
- Search
ProductSpecification/for related existing docs. - List proposed references for user confirmation.
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 · 78 lines · 71 tokens per session scan A 86acdb0a8f63
doc is a skill published in the GitHub repository rakovi4/continue-framework (50 stars, last pushed 5d ago), licensed MIT. It adds 71 tokens to every session and 848 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 2026-08-30.
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…