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 markmhendrickson/neotoma --skill publish-plangit clone --depth 1 https://github.com/markmhendrickson/neotomaWrote 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/markmhendrickson/neotoma/publish-plan)<a href="https://agentmods.dev/skills/markmhendrickson/neotoma/publish-plan"><img src="https://agentmods.dev/badge/skills/markmhendrickson/neotoma/publish-plan/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/markmhendrickson/neotoma/publish-plan"><img src="https://agentmods.dev/badge/skills/markmhendrickson/neotoma/publish-plan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
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 →
- high Prompt Injection · line 6 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- medium Agent Snooping · line 6 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00005 | $0.01488 |
| Opus 5 | $0.00003 | $0.00744 |
| Sonnet 5 | $0.00001 | $0.00298 |
| Haiku 4.5 | $0.00001 | $0.00149 |
Grade A, and why
publish-plan 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 9d 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.
Copies of this mod
2 near-identical copies found in the catalogue:
- publish-plan — 94% identical, 7 lines differ
- publish_plan — 94% identical, 13 lines differ
How it starts
The opening of the file, as written. The whole thing — 219 lines — stays where its author put it; the contents beside it link to each section on GitHub.
name: publish-plan description: Convert a plan file into a GitHub Discussion post for public input. triggers:
- publish plan
- share plan
- publish-plan
- /publish-plan
publish-plan
Convert a plan file (release plan, feature spec, or .cursor/plans/ file) into a
GitHub Discussion post written for external readers. Strips internal references and
PII, rewrites for a public audience, and optionally posts via the GitHub CLI.
When to Use
Use when you have a plan in progress and want external input before execution. Pass the path to any plan document as the argument:
/publish-plan docs/releases/in_progress/v0.12.0/release_plan.md
/publish-plan .cursor/plans/some_plan.md
/publish-plan docs/feature_units/in_progress/FU-2026-01-001/FU-2026-01-001_spec.md
Optionally pass a specific question to ask readers as a second argument:
/publish-plan docs/releases/in_progress/v0.12.0/release_plan.md "Does this sync model work for your use case?"
Step 1: Read and Parse the Plan
- Read the plan file at the provided path.
- Extract the following from the document:
- Goal / motivation: Why does this exist? What problem does it solve?
- Approach / key decisions: What choices were made or are still open?
- Scope boundaries: What is explicitly excluded or deferred?
- Open questions: What is uncertain or unresolved?
Step 2: Strip Internal References
Remove or redact anything that should not be public:
- Full names and email addresses of individuals
- Internal Slack channels, ticket numbers, or system identifiers that leak org structure
- Pricing, cost, or revenue figures
- Internal hostnames, credentials, or environment-specific configuration values
- Agent execution notes (batch status, orchestrator output, FU dependency trees)
- Anything marked
<!-- internal -->or[INTERNAL]
Do not strip:
- Feature IDs (FU-YYYY-MM-NNN) — these are useful public references
- Architecture decisions and technical rationale
- Version numbers and release IDs
- Links to public repo files or issues
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.
- 9d ago First seen · 219 lines · 5 tokens per session scan A ca7cb2f0aff7
publish-plan is a skill published in the GitHub repository markmhendrickson/neotoma (32 stars, last pushed today), licensed MIT. It adds 5 tokens to every session and 1,488 once invoked, about $0.0000 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
akf-trust-metadata
The AI native file format. EXIF for AI — stamps every file with trust scores, source provenance, and compliance metadata. Embeds into 20+ formats (DOCX, PDF, images, code). EU AI Act, SOX, HIPAA auditing.
bilibili_search
Search for videos on Bilibili using keyword queries generated from user interests.
bernstein-approve
Review and approve/reject pending tasks or plans in Bernstein. Use when the user asks about approvals, wants to review agent work, or needs to approve/reject a plan before execution begins.
bernstein-quality
Show quality metrics for Bernstein runs - success rates per model, lint/test pass rates, completion time distributions. Use when the user asks about quality, reliability, which model performs best, or pass rates.
manager
Planning - decompose goals, create tasks via task server.
Supply Chain Security
Software supply chain security — SBOM generation and analysis, dependency confusion and typosquatting detection, malicious package indicators, CI/CD pipeline hardening, and artifact provenance/signing (SLSA, Sigstore).