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 jellydn/my-ai-tools --skill context-discoverygit clone --depth 1 https://github.com/jellydn/my-ai-toolsWrote 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/jellydn/my-ai-tools/context-discovery)<a href="https://agentmods.dev/skills/jellydn/my-ai-tools/context-discovery"><img src="https://agentmods.dev/badge/skills/jellydn/my-ai-tools/context-discovery/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/jellydn/my-ai-tools/context-discovery"><img src="https://agentmods.dev/badge/skills/jellydn/my-ai-tools/context-discovery.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00018 | $0.01059 |
| Opus 5.5 | $0.00007 | $0.00424 |
| Sonnet 5.5 | $0.00004 | $0.00212 |
| Haiku 4.5 | $0.00002 | $0.00106 |
Grade A, and why
context-discovery 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 1mo 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 — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context Discovery
When to Use
Use this skill before and during implementation when:
- Starting work on an unfamiliar module or feature
- The task involves multiple files or systems
- You need to understand existing patterns before coding
- Previous decisions or discussions may be relevant
- You want to avoid duplicating existing functionality
What It Does
Leverages available MCP tools to proactively discover context about the codebase, existing patterns, decisions, and related work. Instead of relying solely on grep/read cycles, it uses purpose-built discovery tools.
Discovery Workflow
Step 1: File Discovery
Find the relevant files using fff:
fff auth # Find auth-related files
fff "*order*" # Find order-related files by pattern
fff config # Find config files
Scan the results to identify the module structure. fff returns frecency-ranked results — the files you access most appear first.
Step 2: Pattern Discovery via sem
Once you know the relevant files, use sem to understand the code's history and structure:
sem blame path/to/file.ts # See who changed each line and when
sem diff main..HEAD -- path/ # See what changed in this area
sem summary path/to/ # Get a summary of the module
sem provides entity-level diffs (function-level, not just file-level), making it easier to understand what actually changed.
Step 3: Historical Context via ctx
Search past agent sessions for relevant context:
ctx search "auth implementation patterns" # Past work on auth
ctx search "this module" path/to/module/ # Past discussions about this area
ctx search "decision" "why did we" path/ # Past decision-making
ctx indexes agent sessions, so you can find past discussions, decisions, and patterns the agent has already encountered.
Step 4: Project Knowledge via qmd
Query durable project knowledge:
qmd query "What architecture decisions exist for X?"
qmd search "authentication patterns"
qmd get ADR-001 # Get a specific ADR
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.
- 1mo ago Changed · -11 tokens per session 6605b2e68bca
- 1mo ago First seen · 133 lines · 29 tokens per session scan A 7b9e925ddbde
context-discovery is a skill published in the GitHub repository jellydn/my-ai-tools (124 stars, last pushed today), licensed MIT. It adds 18 tokens to every session and 1,059 once invoked, about $0.0001 per session on Opus 5.5. 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
context-engineering
Optimizes agent context setup. Use when starting a new session, when agent output quality degrades, when switching between tasks, or when you need to configure rules files and context for a project.
comet-memory
A review step for deciding whether information should become durable personal memory. It can keep, update, forget, or skip memory candidates based on bounded evidence.
relevance-coarse-filter
Cheap, high-recall first-pass filter that removes obvious junk from a detector candidate pool before expensive story-origin research and PR judgment. Decides keep, monitoronly, or reject — never ranks, writes angles, verifies dates, or decides whether to pitch.
recall-memory
Recall relevant long-term memories on demand. Given a topic or question, judges relevance from pre-loaded metadata, loads only relevant files, and returns a concise summary to the main agent.
catchup
Rebuild the human's lost context on a project from live state, in plain language: what needs them, what changed, what new words mean. Use when the human returns after a gap, says they can't follow the project anymore, asks what happened or what a term means, or before deciding what to do next when their mental model…
bailian-memory
A personal memory service and setup guide for storing and retrieving a user's long-term preferences, background, and decisions. It explains when memory may be used and how users can enable, pause, resume, or control it.