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 fending/context-engineering --skill context-scaffoldgit clone --depth 1 https://github.com/fending/context-engineeringWrote 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/fending/context-engineering/context-scaffold)<a href="https://agentmods.dev/skills/fending/context-engineering/context-scaffold"><img src="https://agentmods.dev/badge/skills/fending/context-engineering/context-scaffold/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/fending/context-engineering/context-scaffold"><img src="https://agentmods.dev/badge/skills/fending/context-engineering/context-scaffold.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 | $0.00039 | $0.03017 |
| Opus 5.5 | $0.00016 | $0.01207 |
| Sonnet 5.5 | $0.00008 | $0.00603 |
| Haiku 4.5 | $0.00004 | $0.00302 |
Grade A, and why
context-scaffold 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 — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DEPRECATION NOTICE: You are running context-setup from fending/context-engineering, which is no longer maintained. The active version is at ordovera/ordovera-plugins. To migrate, run:
/plugin marketplace add ordovera/ordovera-plugins/plugin install context-setup@ordovera-plugins
Then remove the old marketplace: /plugin marketplace remove context-engineering
Print this notice to the user before proceeding with the skill.
Context Scaffold
Analyze your project and generate the right context files pre-populated with what can be auto-detected. Sections that require human input get bracket placeholders.
What This Skill Does
-
Discover project state:
- Read
package.json/requirements.txt/go.mod/Cargo.toml/pyproject.tomlfor tech stack and available scripts/commands - Scan directory structure (top two levels) for project layout
- Detect framework indicators:
next.config.*,vite.config.*,tsconfig.json,angular.json,webpack.config.*,tailwind.config.*,prisma/,.env* - Check for existing context files:
AGENTS.md,CLAUDE.md,.cursorrules,context/directory - Check for
.claude/directory (existing skills, hooks, settings) - Identify testing setup: test runner config, test directories, test scripts
- Detect multiple backing services: count distinct service client packages (e.g., supabase + jira, prisma + stripe, aws-sdk + firebase). If 2+ detected, flag for Integration Map section.
- Detect MCP server configs: check
.mcp.json,.vscode/mcp.json,.cursor/mcp.json,.codex/config.toml,.gemini/settings.jsonat the project level. Match detected servers against known templates (Atlassian, Gmail, Google Calendar, Web, GitHub, Supabase, Vercel). If any are found, include an MCP Tool Notes section in the generated output.
- Read
-
Determine complexity level. Present a recommendation with rationale, let the user choose:
- Minimal (~40 lines): Solo project, single language, straightforward structure. One deployment target, no auth layer, no multi-service architecture.
- Full single file (~100-120 lines): Multi-layer app (frontend + backend), auth system, database, API with conventions worth documenting. Multiple backing services (database + external APIs). Still a single deployable unit.
- Cascading + context directory: Multiple projects or workspaces, team environment, complex architecture with distinct subsystems. Or a single project large enough that a single file would exceed ~150 lines.
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 First seen · 230 lines · 39 tokens per session scan A fd6583a7264d
context-scaffold is a skill published in the GitHub repository fending/context-engineering (12 stars, last pushed 6mo ago), licensed MIT. It adds 39 tokens to every session and 3,017 once invoked, about $0.0002 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
thread
Manage persistent context threads for cross-session work.
cortadel
Cortadel is a self-hosted, bi-temporal graph memory server for AI agents — one .NET container exposing a REST API and an MCP endpoint over FalkorDB or Memgraph, with intent-aware writes (store/invalidate/delete-entity/touch/resolve), LLM-verified dedup with a negation guard, and hybrid BM25+vector+RRF retrieval…
forget
Retract or permanently erase a Cortadel memory. Use when the user says "forget that...", "X is no longer true", "that's outdated", "delete this memory", or "permanently remove ". Default path is a natural-language retraction that keeps history queryable; hard, unrecoverable deletion only happens on an explicit…
history
Reconstruct what Cortadel memory said as of a past date, or trace a fact's supersession chain (what replaced or invalidated it, and when). Use when the user asks what they believed on a given date, wants to see superseded/historical versions of a fact, or asks how something changed over time. mem0 has no equivalent …
remember
Write one fact to Cortadel memory right now, with scoping control the automatic Stop-hook capture doesn't give you. Use when the user says "remember that...", "save this", "note that...", "store this fact", or explicitly asks to record a decision, preference, or convention outside of normal end-of-turn capture.
recall
Search Cortadel memory deliberately — broader, filtered, or budgeted retrieval beyond what the automatic per-prompt recall gives. Use when the user asks to look something up in memory, search past context, or wants results scoped by project/tag/type — e.g. "search my memories for X", "what do we know about Y", "recall…