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 xD4O/praxis --skill project-planninggit clone --depth 1 https://github.com/xD4O/praxisWrote 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/xd4o/praxis/project-planning)<a href="https://agentmods.dev/skills/xd4o/praxis/project-planning"><img src="https://agentmods.dev/badge/skills/xd4o/praxis/project-planning/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/xd4o/praxis/project-planning"><img src="https://agentmods.dev/badge/skills/xd4o/praxis/project-planning.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 | $0.00107 | $0.01038 |
| Opus 5.5 | $0.00043 | $0.00415 |
| Sonnet 5.5 | $0.00021 | $0.00208 |
| Haiku 4.5 | $0.00011 | $0.00104 |
Grade A, and why
project-planning 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 15d 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Planning Protocol
EXTREMELY_IMPORTANT: This is a MANDATORY protocol, not a suggestion. Follow every step. Do not skip steps. Do not combine steps. Do not summarize. Work through each gate in order.
A plan is not a list of things to do — it is a sequence chosen so that failure is cheap, progress is visible, and nothing starts before what it depends on exists. A flat to-do list ordered by what came to mind first is the failure this protocol prevents.
STEP 1 — Decompose into done-able tasks
Break the goal into tasks. Apply the test to EACH: "Can I write a testable done-criterion — a state someone else could confirm is reached?" ("done when a request to /login returns a session cookie"). A task you cannot write a done-criterion for is not a task yet — split it, or if it is an open question move it to an unknowns list and mark it for a spike.
STEP 2 — Make dependencies explicit
For each task, name what must already exist before it can start. This ordering is forced by the work, not by preference. A task with no stated dependency is either genuinely foundational (say so) or you have not looked hard enough (look again).
STEP 3 — Pull the riskiest task to the front
Name the single task with the most uncertainty or the highest cost-if-wrong — the one most likely to invalidate the rest of the plan. It goes FIRST, or a timeboxed spike for it does, so a wrong assumption is caught while it is cheap to fix. If your sequence puts it late, re-sequence it or state explicitly why it cannot move earlier.
STEP 4 — Group into demonstrable milestones
Group tasks into milestones. Each milestone must be a state you could SHOW someone — "a user can log in and see their orders" — never an internal-progress label like "phase 1" or "auth 50% done". A milestone with no observable deliverable is a schedule, not a plan.
STEP 5 — Report
PLAN: [goal]
├── Tasks: [task → done-criterion, one line each; unknowns flagged]
├── Dependencies: [what-blocks-what, or "foundational" where none]
├── Riskiest-first: [the task/spike sequenced first, and why it dominates]
├── Milestones: [each a demonstrable state, in order]
└── Confidence: [HIGH / MEDIUM / LOW]
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.
- 15d ago First seen · 87 lines · 107 tokens per session scan A 02ac152a4c83
project-planning is a skill published in the GitHub repository xD4O/praxis (28 stars, last pushed 2mo ago), licensed MIT. It adds 107 tokens to every session and 1,038 once invoked, about $0.0004 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 2026-10-02.
Other skills, from other repositories
story-readiness
Is a story implementation-ready? Checks clear acceptance criteria, open questions, ADR refs. READY/NEEDS WORK/BLOCKED/NOT ASSESSED.
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
projects
List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.
remove
Remove a deployed framework or addon from the current workspace.