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/potato-castle/mono-memory-mcp/api-docsnpx skills add potato-castle/mono-memory-mcp --skill api-docsgit clone --depth 1 https://github.com/potato-castle/mono-memory-mcpWrote 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/potato-castle/mono-memory-mcp/api-docs)<a href="https://agentmods.dev/skills/potato-castle/mono-memory-mcp/api-docs"><img src="https://agentmods.dev/badge/skills/potato-castle/mono-memory-mcp/api-docs.svg" alt="Measured on agentmods" 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 | $0.00014 | $0.00662 |
| Opus 5 | $0.00007 | $0.00331 |
| Sonnet 5 | $0.00003 | $0.00132 |
| Haiku 4.5 | $0.00001 | $0.00066 |
Grade B, and why
api-docs scanned grade B with 2 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 4d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
cat ~/.claude/plugins/mono-memory-mcp/api-docs-template/index.html Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Keep all template features: Try it panels, auth dropdown, param tables, Send/Copy curl How it starts
The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
API Docs Generator
Steps
-
Detect project name from current directory name.
-
Search API-related memories in parallel:
memory_search(query: "API endpoint route", project: "<project>")memory_search(query: "request response schema", project: "<project>")memory_search(query: "API change update", project: "<project>")memory_context(project: "<project>", section: "api")
-
memory_timeline(project: "<project>", limit: 100)— filter API-relevant ones. -
Combine and deduplicate all results.
-
Cache check: Read
.api-docs-cache.jsonif it exists.- Compare memory IDs and
created_atwith cache. - Determine new, updated, removed memories.
- If no changes: print
No changes detected. api-docs.html is up to date.and stop.
- Compare memory IDs and
-
Patch mode (api-docs.html exists AND partial changes):
- Read existing
api-docs.html - Edit only changed endpoint sections (add/update/remove)
- MUST NOT re-read template files
- Skip to step 9
- Read existing
-
Full mode (first run OR too many changes):
- Read template via Bash:
MUST NOT search or explore — just read these 3 files directly.cat ~/.claude/plugins/mono-memory-mcp/api-docs-template/index.html cat ~/.claude/plugins/mono-memory-mcp/api-docs-template/styles.css cat ~/.claude/plugins/mono-memory-mcp/api-docs-template/script.js - Generate single self-contained HTML (inline CSS + JS)
- Group endpoints by base path (e.g.
/api/v1/users/*→ Users) - Keep all template features: Try it panels, auth dropdown, param tables, Send/Copy curl
- Read template via Bash:
-
Save cache
.api-docs-cache.json:{ "generated_at": "<ISO timestamp>", "memories": [{"id": "<uuid>", "created_at": "<timestamp>"}] } -
If no API memories found:
No API-related memories found for project "<project>". Save some first: - memory_save(project: "<project>", content: "GET /api/users - returns paginated user list", tags: "api,endpoint") - memory_init(project: "<project>", section: "api", content: "REST API base URL: /api/v1 ...")
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.
- 4d ago First seen · 75 lines · 14 tokens per session scan B f1f267852f3b
api-docs is a skill published in the GitHub repository potato-castle/mono-memory-mcp (3 stars, last pushed 6mo ago), licensed MIT. It adds 14 tokens to every session and 662 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 2 findings (reads agent configuration directories, makes network calls). 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…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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…