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 me2resh/apexyard --skill processgit clone --depth 1 https://github.com/me2resh/apexyardWrote 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/me2resh/apexyard/process)<a href="https://agentmods.dev/skills/me2resh/apexyard/process"><img src="https://agentmods.dev/badge/skills/me2resh/apexyard/process/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/me2resh/apexyard/process"><img src="https://agentmods.dev/badge/skills/me2resh/apexyard/process.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 388 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 394 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00032 | $0.07498 |
| Opus 5.5 | $0.00013 | $0.02999 |
| Sonnet 5.5 | $0.00006 | $0.01500 |
| Haiku 4.5 | $0.00003 | $0.00750 |
Grade A, and why
process 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 — 539 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing: read docs/skills/shared/writing-rule.md before you write a durable artifact.
/process — BPMN 2.0 from Code, Anchor-Scoped, Cross-Repo-Aware
Maps a named business process from what the codebase actually does to a stakeholder-shareable BPMN 2.0 file. Discovery is anchor-scoped + reachability-bounded — the skill follows only what's connected to the operator-supplied entry point, stops at the connected-component boundary, and crosses repo boundaries only when the target is in apexyard.projects.yaml.
Pairs with /c4 (static system topology) and /extract-features (exhaustive feature inventory) as the "what we already have" tooling family. All three are read-first, ask-only-when-the-code-doesn't-say.
Runtime requirements
| Dependency | Used for | Without it |
|---|---|---|
bash ≥ 4 |
The skill itself | Required |
git |
Anchor resolution + workspace cloning | Required |
gh |
Cross-repo registry lookup | Optional — falls back to registry-only |
xmllint |
XML validity check | Recommended; the smoke test needs it |
python3 ≥ 3.9 |
Grid layout (layout-bpmn.py, standard library only; ET.indent needs 3.9) for <bpmndi> coords |
Without it: the skill warns and emits a bare BPMN (no <bpmndi>). --skip-layout needs no Python. |
node + npx |
bpmnlint for the lint gate only |
Without Node, the lint step cannot run; use --skip-lint to bypass the gate. |
yq |
Registry parsing | Falls back to grep when absent |
Same disclosure shape as docs/getting-started.md § "Optional: LSP-aware code navigation" — disclosed up front, surfaced when invoked, never silently fails.
Path resolution
Read the registry path via portfolio_registry, the per-project docs dir via portfolio_projects_dir, and the workspace dir via portfolio_workspace_dir — all from .claude/hooks/_lib-portfolio-paths.sh. Source the helper at the top of any bash block that touches those paths:
source "$(git rev-parse --show-toplevel)/.claude/hooks/_lib-read-config.sh"
source "$(git rev-parse --show-toplevel)/.claude/hooks/_lib-portfolio-paths.sh"
projects_dir=$(portfolio_projects_dir)
registry=$(portfolio_registry)
workspace_dir=$(portfolio_workspace_dir)
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.
- cross-repo.sh 6.5 KB runs code
- discover.sh 17 KB runs code
- generate-bpmn.sh 14 KB runs code
- layout-bpmn.py 7.5 KB runs code
- lint.sh 3.2 KB runs code
- tests/smoke.sh 12 KB runs code
- tests/test_bpmn_emit.sh 7.5 KB runs code
- tests/test_cross_repo.sh 4.8 KB runs code
- tests/test_process_bpmn.sh 7.9 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.
- 15d ago Changed · +1 lines c9775fdd41cb
- 22d ago Changed · -2 lines bc99133e2083
- 29d ago Changed · +5 lines e10fbc871812
- 1mo ago Changed · +4 lines 17b57a4665f9
- 2mo ago First seen · 531 lines · 32 tokens per session scan A cb85638683e5
process is a skill published in the GitHub repository me2resh/apexyard (542 stars, last pushed yesterday), licensed MIT. It adds 32 tokens to every session and 7,498 once invoked, about $0.0001 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 2026-09-03.
process compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| processme2resh/apexyard | Skill | 542 | yesterday | MIT | A | 32 | Claude Code |
| add-onedrivemicrosoft/power-platform-skills | Skill | 1.1k | yesterday | MIT | A | 33 | Claude Code |
| data-management-planpedrohcgs/claude-code-my-workflow | Skill | 1.7k | 2d ago | MIT | A | 143 | Claude Code |
| product-data-cleanupAlpacaLabsLLC/skills-for-architects | Skill | 402 | 3d ago | MIT | A | 42 | Claude Code |
| ln-25-architecture-diagram-builderlevnikolaevich/claude-code-skills | Skill | 587 | yesterday | MIT | A | 22 | Claude Code |
| blueprint-summarize-summarizereceptron/mulmoterminal | Skill | 261 | yesterday | MIT | A | 54 | Claude Code, Codex |
| 012-agile-epicjabrena/plinth | Skill | 460 | 2d ago | Apache-2.0 | A | 95 | Claude Code, Codex |