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/extracurricular-ai/codex-rewind/path-typesnpx skills add extracurricular-ai/codex-rewind --skill path-typesgit clone --depth 1 https://github.com/extracurricular-ai/codex-rewindWhat 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 | $0.00029 | $0.00507 |
| Opus 5 | $0.00015 | $0.00253 |
| Sonnet 5 | $0.00006 | $0.00101 |
| Haiku 4.5 | $0.00003 | $0.00051 |
Grade A, and why
path-types 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 yesterday.
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.
This is a copy
100% identical to path-types — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Path Types
Apply this guidance when defining new types. Change existing code only when explicitly requested, and keep edits minimal and proportional. Treat these rules as the target state of an ongoing migration; if compliance is difficult, ask the user how to proceed.
- In app-server protocol types, use
LegacyAppPathStringfor backwards compatibility during the URI migration. At the protocol boundary, convert it toPathUriand usePathUriinternally. For host-local logic, such as some config values, useAbsolutePathBuforPathBufinstead. - In exec-server protocol types, use
PathUri. Internally, usePathUriorAbsolutePathBufas appropriate. - In dependencies shared by both servers, use
PathUrior separate APIs that decouple their use cases. - Tool call arguments that the model is expected to generate should be deserialized as regular
Strings with feature-specific path handling code.
Migration requirements
Keep these requirements in mind while migrating code to conform with the above guidelines:
- existing app-server clients keep sending and receiving legacy native-path strings
- app-server can retain and manipulate foreign-platform path URIs
- exec-server APIs use file:// URIs
- local-only operation must not change model-visible text
- model tool arguments may contain raw relative or absolute paths for any OS
- path reasoning must work before the related environment has come online
- URIs cannot explicitly encode the executor’s path convention or operating system
- users must not configure the environment’s OS/path convention explicitly
- URIs should not yet be stored in rollouts, databases, or other persistent storage
- path conversion errors: fail-closed for security-relevant paths, fail-open for UI/diagnostics
- prefer small focused methods on
PathUriorLegacyAppPathStringover local helpers - represent
PathUrivalues as URIs in diagnostics
It is OK if the conversion between paths and URIs is somewhat lossy as long as it will do the right thing for real users.
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.
- yesterday First seen · 44 lines · 29 tokens per session scan A 890145a2ee66
path-types is a skill published in the GitHub repository extracurricular-ai/codex-rewind (44 stars, last pushed 4d ago), licensed Apache-2.0. It adds 29 tokens to every session and 507 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to path-types, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
fast-resume
Search local coding-agent session history and identify safe resume commands. Use when the user asks to find, inspect, continue, or recover previous work from Claude Code, Codex, Pi, or another agent indexed by fast-resume.
intuitive-tests
Use this skill whenever the user asks about unit test best practices, test organization, flat test suites, redundant tests, test refactors, pytest/JUnit/Jest/xUnit layout, test taxonomy, flaky tests, coverage quality, fixtures, mocks, parametrization, pruning existing UTs, or "which tests are worth keeping." It…
intuitive-flow
Stable execution/change router after an approved plan, preflight contract, or tiny concrete task. Refactor-shaped work delegates to intuitive-refactor, and durable work runs through staged planning, review, GSD handoff, implementation, cleanup, and verification while keeping plan ledgers and active capsules compact by…
intuitive-preflight
Turn a vague task, plan, issue, or "LGTM/go ahead" request into an approval-ready preflight contract before implementation starts. Use when the user wants prompt preflight, clearer scope, non-goals, context package, acceptance criteria, definition of done, verification, stop gates, the exact execution command, or…
intuitive-squash
Squash local GSD or agent-generated commit history into a clean, reviewable story while preserving important fixes. Use when the user asks to squash commits, clean git history, compress phase commits, prepare a branch before PR, compare aggressive vs moderate squash options, or preserve hotfix/security commits during…
cross-review
Challenge an existing agent proposal through a small bounded set of independent review perspectives, then judge the findings into one simpler or more defensible recommendation. Use immediately after an agent proposes a solution when the user asks whether there is a simpler approach, wants a second opinion or other…