Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add Ohswedd/praxis/plugin install 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/ohswedd/praxis/claudemd-living)<a href="https://agentmods.dev/skills/ohswedd/praxis/claudemd-living"><img src="https://agentmods.dev/badge/skills/ohswedd/praxis/claudemd-living/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/ohswedd/praxis/claudemd-living"><img src="https://agentmods.dev/badge/skills/ohswedd/praxis/claudemd-living.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 | $0.00112 | $0.00710 |
| Opus 5 | $0.00056 | $0.00355 |
| Sonnet 5 | $0.00022 | $0.00142 |
| Haiku 4.5 | $0.00011 | $0.00071 |
Grade A, and why
claudemd-living 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 10d 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Living CLAUDE.md
CLAUDE.md is loaded into context every session, so it must stay accurate: a stale or contradictory memory file silently degrades every future session. This skill maintains it with the same no-regression discipline praxis applies to code.
When to act
- A build/test/run command changed.
- A new convention, dependency, or architectural pattern was introduced.
- A whole new cohesive subsystem appeared → it may need its own nested file.
- The session audit or your own reading found CLAUDE.md contradicting the code.
- The user asks to update project memory (
/praxis:docs).
Step 1: Locate the right file
Decide the correct scope: a change local to a subsystem belongs in that
subsystem's nested CLAUDE.md, not the root. Only genuinely global facts go in
the root. Create a nested file if the scope warrants one and none exists.
In contributor mode the file praxis maintains is CLAUDE.local.md, which
Claude Code loads alongside the project's CLAUDE.md and appends after it. The
repository's own brief is read, respected, and never edited, reconciled, or
replaced: it is not ours to rewrite, and a diff against it would land in the pull
request. There are no nested files in that mode either, for the same reason; keep
everything in the single local brief.
Step 2: Draft the update
Write the minimal edit that captures the change. Preserve the existing structure
and the <!-- praxis:managed --> marker. Keep it high-signal; do not let the
file bloat.
Step 3: Verify against regression (mandatory)
Before writing, compare the current file with your draft:
python3 ${CLAUDE_PLUGIN_ROOT}/scripts/claudemd_check.py <current> <draft>
Then dispatch @praxis:claudemd-verifier with both versions. The verifier
confirms the draft does not:
- drop a still-valid instruction,
- remove a build/test/run command that still applies,
- contradict another part of the file,
- shrink the file by silently losing content.
Any structural regression the checker flags must be explained and justified by
the verifier (e.g. "the npm run e2e command was removed because that script no
longer exists") before it is accepted.
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.
- 10d ago First seen · 63 lines · 112 tokens per session scan A f9feed22d214
claudemd-living is a skill published in the GitHub repository Ohswedd/praxis (1 stars, last pushed 1mo ago), licensed MIT. It adds 112 tokens to every session and 710 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
scroll-craft
Build premium scroll-driven landing pages for service, product, food, and drink brands. Plan the visitor journey, page grammar, emotional peak, and bespoke signature move. Create dimensional heroes with independent visual planes, restrained motion, and separate mobile composition. Use supplied photos and footage or…
dream
Prunes and consolidates the project's auto-memory to keep it minimal — deletes stale, wrong, or redundant memories, merges overlapping ones into existing files, and trims the index. Strong bias against growth: never creates new memory files and never stores new facts. Verifies staleness against the current codebase…
masterplan-detect
Suggest /masterplan import only when legacy masterplan bundle state files (docs/masterplan/ /state.yml at schema 5.x) exist without a matching v8 run. Generic planning artifacts (PLAN.md, TODO.md, ROADMAP.md, design docs, PR task lists) are NOT importable — no /masterplan import can ingest them; mention them only as…
foreman
Run a website build as the brain agent. Interview the user, force the scope and design decisions they would otherwise skip, lock a visual system, write one high-quality build brief, then either build it in this session or hand it to a coding agent (Codex, Claude Code, or any harness), and verify and ship it live. Use…
skill-creator
Authors and audits Claude Code skills: frontmatter, directory layout, scope, invocation control, and bundled references or scripts.
git-master
Git expert: atomic commits with style detection, rebase and squash, and history archaeology through blame, bisect and pickaxe.