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 pantheon-org/tekhne --skill plan-creategit clone --depth 1 https://github.com/pantheon-org/tekhneWrote 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/pantheon-org/tekhne/plan-create)<a href="https://agentmods.dev/skills/pantheon-org/tekhne/plan-create"><img src="https://agentmods.dev/badge/skills/pantheon-org/tekhne/plan-create/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/pantheon-org/tekhne/plan-create"><img src="https://agentmods.dev/badge/skills/pantheon-org/tekhne/plan-create.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00113 | $0.02929 |
| Opus 5 | $0.00056 | $0.01465 |
| Sonnet 5 | $0.00023 | $0.00586 |
| Haiku 4.5 | $0.00011 | $0.00293 |
Grade A, and why
plan-create 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.
How it starts
The opening of the file, as written. The whole thing — 265 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan Create -- Structured Plan Scaffolding
Create .context/plans/ files that pass structural validation and match
local conventions. The workflow ensures every plan has valid frontmatter,
clear phases and tasks, and can be immediately reviewed by the
plan-review skill.
Prerequisites
- A clear idea of the work to be planned (goal, scope, implementation steps)
- The
context-fileskill available if frontmatter repair is needed - The
plan-reviewskill available for post-creation validation (optional) - Shell access to run validation scripts
When to Use
- Drafting a new implementation plan with multiple phases
- Scoping work that needs review before implementation begins
- Creating a plan that will later be audited by
plan-review
When NOT to Use
- For the main project SKILL.md or agent skills -- use the skill template instead
- For one-off notes or scratch files -- use inline notes
- When the work is trivially small (1 step, no phases) -- just write a finding
Workflow
1. Gather the plan specification
Ask the user about the plan. Collect at minimum:
- Goal -- what does success look like? What problem is being solved?
- Scope -- what's in and what's out? Are there known constraints?
- Phases -- what are the sequential stages? Each phase should:
- Have a clear deliverable or exit criterion
- Be independently shippable (could stop after this phase)
- Be 2–5 tasks, not 20+
- Tasks per phase -- for each phase, list concrete work units:
- Each task should be completable in a single session (hours, not weeks)
- Use actionable language ("Add --format flag", not "Improve output")
- Flag which tasks can run in parallel (waves)
- Dependencies -- does this plan depend on other plans, PRs, or external work?
- Risks -- what could go wrong? What's the biggest unknown?
- Timeline -- optional, if the user has a deadline or priority
- Effort -- a T-shirt-sized estimate. Value -- a benefit-of-action grade. Themes -- an ordered subject-area tag list. All three are required frontmatter fields; see Grading Effort, Value, and Themes for the full rubric, allowed values, and worked examples. TYPICALLY these three fields are the ones a first-time plan author gets wrong -- read the reference before guessing.
What ships with it
19 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.
- assets/schemas/plan-scaffold.schema.json 4.4 KB
- assets/templates/plan-scaffold.yaml 2.5 KB
- evals/instructions.json 3.4 KB
- evals/scenario-01/capability.txt 129 B
- evals/scenario-01/criteria.json 1.8 KB
- evals/scenario-01/task.md 2.4 KB
- evals/scenario-02/capability.txt 132 B
- evals/scenario-02/criteria.json 2.0 KB
- evals/scenario-02/task.md 2.0 KB
- evals/scenario-03/capability.txt 134 B
- evals/scenario-03/criteria.json 1.9 KB
- evals/scenario-03/task.md 1.8 KB
- evals/scenario-04/capability.txt 146 B
- evals/scenario-04/criteria.json 1.8 KB
- evals/scenario-04/task.md 2.2 KB
- evals/summary.json 155 B
- references/grading-effort-value-themes.md 3.0 KB
- references/plan-structure.md 1.6 KB
- scripts/validate-plan-scaffold.sh 2.4 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.
- 9d ago First seen · 265 lines · 113 tokens per session scan A c09259b0c16d
plan-create is a skill published in the GitHub repository pantheon-org/tekhne (10 stars, last pushed yesterday), licensed MIT. It adds 113 tokens to every session and 2,929 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 2026-09-03.
Other skills, from other repositories
claude-md-improver
Audit and improve CLAUDE.md files in repositories. Use when user asks to check, audit, update, improve, or fix CLAUDE.md files. Scans for all CLAUDE.md files, evaluates quality against templates, outputs quality report, then makes targeted updates. Also use when the user mentions "CLAUDE.md maintenance" or "project…
gke-reliability
Improves GKE workload reliability, using PDBs, health probes, and topology spread constraints. Use when configuring GKE workload reliability, setting up PDBs, or configuring GKE health probes (liveness, readiness, startup). Don't use for disaster recovery setup or full cluster backups (use gke-backup-dr instead).
gke-workload-security
Audits, configures, and hardens workload-level security controls for Google Kubernetes Engine (GKE) applications and namespaces. Covers running cluster security audits (auditcluster.sh), configuring Workload Identity Federation (impersonation, KSA/GSA binding, and pod setup), enforcing Network Policies (default-deny…
atlas-obscura
Search Atlas Obscura for weird, wonderful, and hidden gem places near any destination. Find the interesting stuff, not boring plaques. Search by coordinates, get full details with descriptions and images.
agent-code-generator
Generates Agent definitions (.md files) based on user intent and standard templates.
cf-validate
A validator for 1C configuration source files. It checks the XML structure and the files and objects that make up a 1C business-application configuration.