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 codebase-alignmentgit 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/codebase-alignment)<a href="https://agentmods.dev/skills/pantheon-org/tekhne/codebase-alignment"><img src="https://agentmods.dev/badge/skills/pantheon-org/tekhne/codebase-alignment/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/codebase-alignment"><img src="https://agentmods.dev/badge/skills/pantheon-org/tekhne/codebase-alignment.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 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 Excessive Agency · line 66 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 154 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 176 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 172 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00064 | $0.02100 |
| Opus 5 | $0.00032 | $0.01050 |
| Sonnet 5 | $0.00013 | $0.00420 |
| Haiku 4.5 | $0.00006 | $0.00210 |
Grade A, and why
codebase-alignment 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 — 223 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codebase Alignment — Audit a Codebase Against User-Provided Standards
Systematically checks every file in a codebase against human-readable standards the user supplies, reports violations grouped by file and convention, and offers to fix them.
Mindset
The model MUST NOT guess or assume the standards. This is the core constraint. If the user says "align this with our conventions" without spelling them out, stop and ask. Standards that are assumed are standards that are wrong.
Conventions that cannot be checked at all (subjective design preferences, naming that depends on context) should be reported as "manual review needed" — do not pretend an objective check was run when one wasn't.
Fix suggestions are best-effort. When a violation is ambiguous (e.g. a naming convention that could be fixed multiple ways), flag it for the user rather than guessing.
When to Use
- Onboarding a new team member who needs the codebase brought in line with docs
- After adopting a new style guide or coding standard
- Before a major release or code review sprint
- When migrating a codebase and need to verify alignment with target conventions
- When the user says "audit this codebase", "align with our standards", "check our conventions", "does this follow our style guide"
If the user already has automated linting catching everything, prefer standards-to-tooling to codify the rules instead — this skill is for ad-hoc or partially-automated conventions.
When NOT to Use
- The user already has automated linting/formatting catching everything (point
them to
standards-to-toolinginstead to codify the rules) - The user has not provided standards and refuses to (do not proceed)
- The task is a simple mechanical refactor with no judgment calls
- Standards are being changed mid-review — ask to finalise them first
- The codebase is entirely generated or compiled output (vendored deps, build artifacts)
- Standards reference a language or framework not present in this project — align tooling first
What ships with it
27 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.
- evals/instructions.json 1.4 KB
- evals/scenario-01/capability.txt 86 B
- evals/scenario-01/criteria.json 819 B
- evals/scenario-01/task.md 1.3 KB
- evals/scenario-02/capability.txt 116 B
- evals/scenario-02/criteria.json 870 B
- evals/scenario-02/task.md 1.5 KB
- evals/scenario-03/capability.txt 91 B
- evals/scenario-03/criteria.json 984 B
- evals/scenario-03/task.md 1.8 KB
- evals/scenario-04/capability.txt 112 B
- evals/scenario-04/criteria.json 820 B
- evals/scenario-04/task.md 1.4 KB
- evals/scenario-05/capability.txt 111 B
- evals/scenario-05/criteria.json 965 B
- evals/scenario-05/task.md 1.6 KB
- evals/scenario-06/capability.txt 115 B
- evals/scenario-06/criteria.json 746 B
- evals/scenario-06/task.md 1.3 KB
- evals/scenario-07/capability.txt 101 B
- evals/scenario-07/criteria.json 751 B
- evals/scenario-07/task.md 1.1 KB
- evals/scenario-08/capability.txt 130 B
- evals/scenario-08/criteria.json 719 B
- evals/scenario-08/task.md 1.6 KB
- evals/summary.json 861 B
- references/edge-cases.md 3.5 KB
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 · 223 lines · 64 tokens per session scan A 0bd6da68391f
codebase-alignment is a skill published in the GitHub repository pantheon-org/tekhne (10 stars, last pushed yesterday), licensed MIT. It adds 64 tokens to every session and 2,100 once invoked, about $0.0003 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
agent-watchdog
Use when asked to watch, babysit, audit, review, compare, or fix another agent's work from a Codex session ID, Claude Code session/transcript, chat/thread link, PR, branch, log, or pasted run summary. Monitor until the other agent is done or blocked, reconstruct what the user asked, independently investigate the same…
agent-design-best-practices
Best practices for designing Claude Code agent files (.claude/agents/.md). This skill should be used when writing or reviewing agent markdown files to ensure proper design with focused domains, correct tool access, reusable definitions, and separation of capabilities from lifecycle. Combines Anthropic's official…
graphify-dotnet
Use graphify-dotnet to generate codebase knowledge graphs, architecture snapshots, and exportable repository maps from .NET or polyglot source trees, with optional AI-enriched semantic relationships. USE FOR: graphify commands; graph JSON, HTML, SVG, Cypher, Markdown, and Obsidian exports; repository map and…
map-codebase
Deep architecture report that fans out parallel inspections across different aspects of the codebase (structure, tech stack, APIs, patterns, data flow, dependencies, testing) and synthesizes findings into a comprehensive document at .turbo/codebase-map.md and .turbo/codebase-map.html. Use when the user asks to "map…
sonarqube-mcp
Provides SonarQube and SonarCloud integration patterns via the Model Context Protocol (MCP) server. Enables quality gate monitoring, issue discovery and triaging, pre-push code analysis, and rule education directly in the agent workflow. Use when the user wants to check quality gates, search for Sonar issues, analyze…
reply-to-pr-threads
Draft, confirm, and post replies to GitHub PR review threads. Handles per-category reply formatting, re-fetches thread resolution state so auto-resolved threads are skipped, and posts via GraphQL. Use when the user asks to "reply to PR threads", "post PR thread replies", or "draft PR reply messages".