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 Immortalqx/my_codex_skills --skill update-source-mapgit clone --depth 1 https://github.com/Immortalqx/my_codex_skillsWrote 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/immortalqx/my_codex_skills/update-source-map)<a href="https://agentmods.dev/skills/immortalqx/my_codex_skills/update-source-map"><img src="https://agentmods.dev/badge/skills/immortalqx/my_codex_skills/update-source-map.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 5.1 | $0.00156 | $0.02034 |
| Opus 5 | $0.00078 | $0.01017 |
| Sonnet 5 | $0.00031 | $0.00407 |
| Haiku 4.5 | $0.00016 | $0.00203 |
Grade A, and why
update-source-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 — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Update Source Map
Overview
Build (or refresh) a structured index of a project directory. The skill always produces a Markdown SOURCE_MAP.md (primary, human-readable) and a JSON source_map.json (programmatic). A hand-curated curated_summaries.json is preserved across regenerations so curated per-file knowledge compounds over time.
When this skill runs
Trigger on requests like: - "build a source map for this project" - "update the source map" - "create a project index" - any task where Codex is about to do work in a workspace it doesn't already know well
Do not trigger for: code refactoring, single-file edits, paper reading, or tasks unrelated to project navigation.
Workflow
Step 1 — Decide mode (auto-detect)
Run scripts/detect_existing.py <workspace_root> to decide between create and update mode. Detection priority:
<workspace>/x_temp/SOURCE_MAP.md+x_temp/source_map.json→ update<workspace>/SOURCE_MAP.md+source_map.json→ update<workspace>/.codex/source_map.json→ update- Otherwise → create
The detection JSON has fields: mode, md_path, json_path, found_at. Pass --force-mode create|update to override.
If detection returns partial: true (only one of the two files exists), warn the user before proceeding.
Step 2 — Confirm the Run Plan
Before any execution, report the plan:
- Which mode (create / update) and why
- Which workspace to scan
- Where the outputs will go (default:
<workspace>/x_temp/) - Any custom exclusions or extensions
- Estimated file count from a quick
find(to set expectations)
If the user explicitly asked you to build or update the source map, proceed after stating the plan. If the user only asked what would happen, stop after the plan.
Step 3 — Setup
Create the output directory if it doesn't exist:
mkdir -p <workspace>/x_temp
For update mode with diff support, also keep the previous inventory:
mv <workspace>/x_temp/file_inventory.jsonl <workspace>/x_temp/file_inventory.prev.jsonl
(only if regeneration would otherwise lose it)
What ships with it
9 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.
- agents/openai.yaml 318 B
- references/create-vs-update.md 2.1 KB
- references/exclusions-default.md 1.7 KB
- references/format-spec.md 2.7 KB
- scripts/build_source_map.py 15 KB runs code
- scripts/detect_existing.py 2.5 KB runs code
- scripts/extract_headings.py 1.3 KB runs code
- scripts/regenerate.py 6.0 KB runs code
- scripts/scan_workspace.py 5.1 KB runs code
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 · 160 lines · 156 tokens per session scan A 8c2e7f76e242
update-source-map is a skill published in the GitHub repository Immortalqx/my_codex_skills (51 stars, last pushed 1mo ago), licensed MIT. It adds 156 tokens to every session and 2,034 once invoked, about $0.0008 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
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.