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 rules-managementgit 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/rules-management)<a href="https://agentmods.dev/skills/pantheon-org/tekhne/rules-management"><img src="https://agentmods.dev/badge/skills/pantheon-org/tekhne/rules-management.svg" alt="Measured on agentmods" 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 | $0.00147 | $0.01460 |
| Opus 5 | $0.00073 | $0.00730 |
| Sonnet 5 | $0.00029 | $0.00292 |
| Haiku 4.5 | $0.00015 | $0.00146 |
Grade B, and why
rules-management scanned grade B with 1 finding 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 7d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
cat .claude/RULES.md How it starts
The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rules Management
Manage project-level agent behavioural rules.
Prerequisites
- The rules file (path shown in Quick Start below) must exist in the repository root. If it is missing, create it with a
# Agent Rulesheading first. - Only invoke this skill when the user explicitly requests a new rule -- do not infer rule creation from unrelated conversation.
- Depends on the user providing a clear behavioural directive; if the instruction is vague, ask for clarification before writing.
- The rule schema (
assets/schemas/rule-entry.schema.json) and template (assets/templates/rule-entry.yaml) define the structured title/directive/rationale shape a rule entry MUST have.
Quick Start
# Read current rules
cat .claude/RULES.md
# Validate the rules file against the schema before or after editing it
./scripts/validate-rules.sh validate .claude/RULES.md
# Generate a correctly-formatted entry from the template instead of hand-writing one
./scripts/validate-rules.sh generate "<title>" "<directive>" "<rationale>"
→ Produces the full current ruleset for duplicate checking, and a schema-validated way to both read and write entries.
Where Rules Live
All agent rules reside in a single file (path shown in Quick Start above). This is the authoritative source that all agents read before acting in this repository.
When to Use
Create a new rule whenever the user says something like:
- "New rule: ..."
- "Add a rule that ..."
- "Record that ..."
- "Make a rule about ..."
- "Codify this as a rule"
- "Note this" / "Take note of ..."
- "New instruction: ..."
The user's instruction becomes the rule body. You MUST:
- Read the existing rules file first (see Quick Start) -- check every
### Rule:heading to avoid duplicates - If a rule with the same directive already exists, inform the user and do NOT create a duplicate
- Append the new rule following the format below -- PREFER
scripts/validate-rules.sh generateover hand-typing the three-line block - Inform the user you've added it
- Confirm by running
scripts/validate-rules.sh validatebefore treating the change as done -- TYPICALLY this is the same command as the Quick Start validation step
What ships with it
18 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/rule-entry.schema.json 735 B
- assets/templates/rule-entry.yaml 222 B
- evals/instructions.json 2.6 KB
- evals/scenario-01/capability.txt 132 B
- evals/scenario-01/criteria.json 1.2 KB
- evals/scenario-01/task.md 1.1 KB
- evals/scenario-02/capability.txt 121 B
- evals/scenario-02/criteria.json 1.0 KB
- evals/scenario-02/task.md 1.0 KB
- evals/scenario-03/capability.txt 119 B
- evals/scenario-03/criteria.json 1.2 KB
- evals/scenario-03/task.md 1.2 KB
- evals/scenario-04/capability.txt 99 B
- evals/scenario-04/criteria.json 1.3 KB
- evals/scenario-04/task.md 1.6 KB
- evals/summary.json 633 B
- references/rule-format.md 693 B
- scripts/validate-rules.sh 6.4 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.
- 7d ago First seen · 141 lines · 147 tokens per session scan B 4068b5cd4a2f
rules-management is a skill published in the GitHub repository pantheon-org/tekhne (10 stars, last pushed 6d ago), licensed MIT. It adds 147 tokens to every session and 1,460 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
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-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…
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).
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.
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.
agent-code-generator
Generates Agent definitions (.md files) based on user intent and standard templates.