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/shinpr/codex-workflows/external-resource-contextnpx skills add shinpr/codex-workflows --skill external-resource-contextgit clone --depth 1 https://github.com/shinpr/codex-workflowsWhat 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 | $0.00032 | $0.01083 |
| Opus 5 | $0.00016 | $0.00541 |
| Sonnet 5 | $0.00006 | $0.00217 |
| Haiku 4.5 | $0.00003 | $0.00108 |
Grade A, and why
external-resource-context 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
External Resource Context
Purpose
This skill resolves a concrete external evidence dependency for a current design or verification decision, records its stable access method, and lets later consumers reuse that evidence.
Potential resources include design origin, design system, API or database schema sources, IaC, and verification environments. A workflow selects only the resource axis needed by its current decision.
Scope Boundaries
In scope: resolving a named external evidence need, storage location, single-source ownership, and lookup of a known resource.
Freshness handling: record access methods and feature identifiers here. The consuming workflow checks current resource content at use time.
Storage Locations
| Tier | Location | Holds | Update Frequency |
|---|---|---|---|
| Project | docs/project-context/external-resources.md |
Environment-stable facts: resource labels, presence, and access methods | When the project environment changes |
| Feature | ## External Resources Used section in the relevant UI Spec or Design Doc |
Feature-specific identifiers that reference project-tier labels | Per feature |
Single Source Rule
The project tier owns environment facts such as URLs, MCP server names, file paths, commands, and secret-store locations. Feature-tier sections list feature-specific identifiers such as design node ids, API paths, schema names, or IaC module names, then reference the project-tier label.
Hearing Protocol
When to Hear
| Condition | Action |
|---|---|
| Repository or supplied evidence resolves the current decision | Continue without hearing |
| A recorded matching axis has a usable access method | Reuse it without hearing |
| A named axis required by the current decision is missing or stale | Ask only for that axis and the access method needed to inspect it |
State which decision or verification result the requested resource controls. Leave unrelated axes unrecorded. Use N/A only for a selected or inspected axis confirmed to be outside the project.
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 102 lines · 32 tokens per session scan A dc2fe261d674
external-resource-context is a skill published in the GitHub repository shinpr/codex-workflows (38 stars, last pushed 5d ago), licensed MIT. It adds 32 tokens to every session and 1,083 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 2026-08-30.
Other skills, from other repositories
chrome-cdp
Drive a headless Chrome over the Chrome DevTools Protocol (CDP) for browser QA — navigate, click, fill forms, read the DOM/accessibility tree, screenshot, and assert. Use whenever a task requires loading a web page and interacting with it like a user. Chrome is launched by a bash step (recipe below); this skill…
skill-creator
Create, install, or update skills in the workspace. Use when (1) installing a skill from a URL or remote source, (2) creating a new skill from scratch, (3) updating or restructuring existing skills. Always use this skill for any skill installation or creation task.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
imsg
Use imsg to read and send iMessage/SMS via macOS Messages.app.
ax-python-agent
Use when writing Python code with axllm for agents, child delegation, tools, MCP, citations, persistent playbook learning, stage instructions, runtime state, final typed responses, and direct-respond executor skipping.
ax-cpp-agent-rlm
Use when writing C++ code with axllm for RLM executor loops, AxCodeRuntime sessions, runtime envelopes, process runtimes, and optional runtime profiles.