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 athola/claude-night-market --skill context-mapgit clone --depth 1 https://github.com/athola/claude-night-marketWrote 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/athola/claude-night-market/context-map)<a href="https://agentmods.dev/skills/athola/claude-night-market/context-map"><img src="https://agentmods.dev/badge/skills/athola/claude-night-market/context-map/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/athola/claude-night-market/context-map"><img src="https://agentmods.dev/badge/skills/athola/claude-night-market/context-map.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 | $0.00032 | $0.01133 |
| Opus 5 | $0.00016 | $0.00566 |
| Sonnet 5 | $0.00006 | $0.00227 |
| Haiku 4.5 | $0.00003 | $0.00113 |
Grade A, and why
context-map 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 7d 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 — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context Map
Generate a compressed context map for the current project. The map pre-compiles structural knowledge that AI assistants would otherwise discover through expensive Read/Grep calls, saving thousands of tokens per session.
When To Use
- At the start of a session to understand project layout
- Before implementing features to identify entry points
- When exploring an unfamiliar codebase
- To reduce token waste from Read calls
- To identify hot files (high blast radius) before changes
When NOT To Use
- Context is already over budget mid-session (use
conserve:clear-context) - Auditing the codebase for bloat (use
conserve:bloat-detector)
What It Detects
| Category | Description |
|---|---|
| Structure | Directory layout with file counts and languages |
| Dependencies | Multi-ecosystem: Python, Node, Rust, Go, Java |
| Frameworks | Framework detection from dependency analysis |
| Entry Points | main.py, index.ts, CLI scripts, etc. |
| Import Graph | File-to-file import relationships |
| Hot Files | Files imported by 3+ others (high blast radius) |
| Routes | FastAPI, Flask, Express, Hono API endpoints |
| Env Vars | Environment variable references with defaults |
| Middleware | Auth, CORS, rate-limit, logging patterns |
| Models/Schemas | SQLAlchemy, Django, Pydantic, Prisma definitions |
| Token Savings | Estimated tokens saved vs manual exploration |
Procedure
- Run the scanner on the project root:
PYTHONPATH="$(find . -path '*/conserve/scripts' -type d \
-print -quit 2>/dev/null || \
echo 'plugins/conserve/scripts')" \
python3 -m context_scanner .
-
Present the output to the user as the project overview.
-
Use the context map to guide subsequent file reads. Prioritize hot files and entry points first.
Options
Output
--format jsonfor structured output--max-tokens Nto adjust output size (default: 5000)--output FILEto save to a file
Modes
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.
- 7d ago First seen · 164 lines · 32 tokens per session scan A 75c9c9dfa626
context-map is a skill published in the GitHub repository athola/claude-night-market (337 stars, last pushed today), licensed MIT. It adds 32 tokens to every session and 1,133 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
auto-context
An automatic context detector that identifies the files, functions, and other code context an AI needs for a task.
context-engineering
Use this skill for optimizing AI context windows. Covers context sizing, prioritization, and avoiding context overflow.
cortivex-context-compression
Compress agent outputs for efficient context handoff between pipeline nodes while preserving actionable information.
project-wiki
A system for creating and maintaining a project wiki: a set of organized documents that explain a software project's plans, rules, references, and progress.
plugin-core-builtin-migration
A repeatable process for turning an optional MindOS renderer plugin into a built-in, always-available part of the application. It also covers moving old entry points while keeping existing data usable.
ask
Adaptive vault reader skill. Receives a natural language question, searches the vault first (Glob/Grep, entity reads, wikilink traversal), then self-assesses whether more context is needed. Escalates to /graphify for graph-level understanding or to /bedrock:teach for remote content ingestion only when the vault alone…