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 whygit 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/why)<a href="https://agentmods.dev/skills/pantheon-org/tekhne/why"><img src="https://agentmods.dev/badge/skills/pantheon-org/tekhne/why/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/why"><img src="https://agentmods.dev/badge/skills/pantheon-org/tekhne/why.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 | $0.00143 | $0.06323 |
| Opus 5 | $0.00072 | $0.03161 |
| Sonnet 5 | $0.00029 | $0.01265 |
| Haiku 4.5 | $0.00014 | $0.00632 |
Grade A, and why
why 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 — 378 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Why
Ported from the
whyskill in cursor/plugins pstack — Cursor, a separate AI-coding-editor product, not to be confused with a text/DB cursor — for use with this harness'sAgenttool. Agent-spawning mechanics use this repo's actual subagent types and model/effort params in place of the original's source-specific model names andreadonlyflag; MCP discovery is adapted to how this session surfaces connected servers.Git-history steps prefer a code-graph MCP first, when one is connected. If your environment has one (e.g.
tokensave), prefer its graph tools over raw shell git commands for codebase research wherever an equivalent exists — a per-symbol blame/log tool gives structural history tracked across renames and is the first move for any target that's a function, method, class, or type. Rawgit blame/git log --follow -pare the fallback for what a code-graph tool doesn't cover (or for when none is connected): line-precise blame that doesn't align to a symbol boundary, full raw patch text, or file kinds outside the tool's indexed languages. A semantic added/removed/modified-symbol diff tool, if available, is cheaper to read than a raw patch before deciding which commits are worth opening in full. See Step 2 for the full mapping. If such a tool reports a stale index for the current worktree, fall back to raw git for that worktree's own uncommitted or unindexed changes.Map your own MCP stack before spawning investigators — don't assume any of these are connected. Source-control-hosting MCPs (GitLab, GitHub) commonly double as the issue-tracker category too; issue-tracker/long-form-docs MCPs (e.g. Jira/Confluence) commonly split into two investigators, one per product; chat MCPs (e.g. Slack) cover real-time chat. Infrastructure observability, error tracking, and product-analytics-warehouse MCPs (Datadog, Sentry, a data warehouse) are frequently absent — when they are, their investigators should come back "skipped, no MCP available," which is an honest gap, not a failure to search harder. If the repo has no remote, source-control investigation is local git (or code-graph) history only — skip straight to that rather than treating the absence of
gh pr view/remote MR tooling as a search failure.
Investigate the motivation and intent behind code. Why was it built this way? What edge cases were considered? What product, business, or operational constraints shaped the design? What alternatives were rejected, and why?
Companion to the how skill. how answers what the code does and how it works. why answers what forces led to its shape.
What ships with it
32 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.
- .audits/2026-08-22/Analysis.md 478 B
- .audits/2026-08-22/audit.json 541 B
- .audits/2026-08-22/Remediation.md 1.4 KB
- evals/instructions.json 2.7 KB
- evals/scenario-01/capability.txt 145 B
- evals/scenario-01/criteria.json 1.2 KB
- evals/scenario-01/task.md 1.7 KB
- evals/scenario-02/capability.txt 139 B
- evals/scenario-02/criteria.json 1.2 KB
- evals/scenario-02/task.md 1.7 KB
- evals/scenario-03/capability.txt 135 B
- evals/scenario-03/criteria.json 1.2 KB
- evals/scenario-03/task.md 1.8 KB
- evals/scenario-04/capability.txt 187 B
- evals/scenario-04/criteria.json 783 B
- evals/scenario-04/task.md 1.8 KB
- evals/scenario-05/capability.txt 115 B
- evals/scenario-05/criteria.json 720 B
- evals/scenario-05/task.md 1.9 KB
- evals/summary.json 249 B
- references/epistemics.md 7.6 KB
- references/investigator-prompt.md 7.0 KB
- references/source-playbook.md 1.9 KB
- references/sources/code-archaeology.md 5.5 KB
- references/sources/databricks.md 5.2 KB
- references/sources/datadog.md 4.6 KB
- references/sources/incident-postmortem.md 2.2 KB
- references/sources/linear.md 3.3 KB
- references/sources/notion.md 2.9 KB
- references/sources/sentry.md 4.4 KB
- references/sources/slack.md 3.0 KB
- references/synthesizer-prompt.md 7.8 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 · 378 lines · 143 tokens per session scan A 996b3e7243fa
why is a skill published in the GitHub repository pantheon-org/tekhne (10 stars, last pushed yesterday), licensed MIT. It adds 143 tokens to every session and 6,323 once invoked, about $0.0007 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.