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 chhuax/praxis-devos --skill openspec-apply-changegit clone --depth 1 https://github.com/chhuax/praxis-devosWrote 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/chhuax/praxis-devos/openspec-apply-change)<a href="https://agentmods.dev/skills/chhuax/praxis-devos/openspec-apply-change"><img src="https://agentmods.dev/badge/skills/chhuax/praxis-devos/openspec-apply-change.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 | $0.00053 | $0.01829 |
| Opus 5 | $0.00026 | $0.00915 |
| Sonnet 5 | $0.00011 | $0.00366 |
| Haiku 4.5 | $0.00005 | $0.00183 |
Grade A, and why
openspec-apply-change 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 — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implement tasks within an OpenSpec change. You may advance through one or more unlocked tasks in tasks.md order until they are completed, blocked, or the user asks you to pause.
Core Positioning
- OpenSpec owns change selection, reading
contextFiles, identifying the current implementation slice, and maintainingtasks.mdstatus - Superpowers owns slice refinement, execution mode, TDD, debugging, and verification
tasks.mdis the default source of truth for tasks- Do not generate a second master plan for the entire change
Exact Skill Protocol
- When this route is matched, you must call the corresponding exact skill name
- Do not substitute a similar local skill, TodoWrite, manual task breakdown, or long-form reasoning
- If the exact skill is unavailable, report that explicitly and pause the current routing
- Before the current change and implementation slice are locked, do not create TodoWrite items, list execution todos, or enter implementation planning
Capability Routing
1. Task refinement
By default, call superpowers:writing-plans first for the current implementation slice.
You may skip this only when the task is a very small change such as pure wording edits, mechanical renames, or formatting cleanup.
The scope of writing-plans is limited to the current implementation slice, not the whole change and not a separate plan file.
2. Execution mode routing
After writing-plans, do not jump straight into implementation. You must choose one of these two paths:
- If there is independent sub-work that can run in parallel:
superpowers:subagent-driven-development - Otherwise:
superpowers:executing-plans
Unless you have clearly identified independent sub-work that can run in parallel, default to superpowers:executing-plans.
Before execution mode is confirmed, do not:
- Create TodoWrite entries
- Run test commands
- Start patching or coding
- Call implementation-oriented helper skills
Before starting implementation, you must explicitly output an "execution mode confirmation" that includes at least:
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 · 192 lines · 53 tokens per session scan A 489764a6ed81
openspec-apply-change is a skill published in the GitHub repository chhuax/praxis-devos (21 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 53 tokens to every session and 1,829 once invoked, about $0.0003 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
engram-testing-coverage
TDD and coverage standards for Engram. Trigger: When implementing behavior changes in any package.
nw-fp-clojure
Clojure language-specific patterns, data-first modeling, REPL-driven development, and spec.
strict-tdd
Strict RED->GREEN->REFACTOR test-driven development with enforcement. Never write production code before a failing test. Atomic commits per TDD cycle.
tdd
This skill should be used when the user wants to implement features or fix bugs using test-driven development. Enforces the RED-GREEN-REFACTOR cycle with vertical slicing, context isolation between test writing and implementation, human checkpoints, and auto-test feedback loops. Uses multi-agent orchestration with the…
conductor-implement
Execute tasks from a track's implementation plan following TDD workflow.
mobiai-mobile-tdd
You MUST use this before writing any implementation code for a mobile feature, bug fix, refactor, or behavior change. Tests come before implementation — no exceptions.