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 create-contextgit 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/create-context)<a href="https://agentmods.dev/skills/pantheon-org/tekhne/create-context"><img src="https://agentmods.dev/badge/skills/pantheon-org/tekhne/create-context/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/create-context"><img src="https://agentmods.dev/badge/skills/pantheon-org/tekhne/create-context.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 | $0.00076 | $0.01331 |
| Opus 5.5 | $0.00030 | $0.00532 |
| Sonnet 5.5 | $0.00015 | $0.00266 |
| Haiku 4.5 | $0.00008 | $0.00133 |
Grade A, and why
create-context 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 10d 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create Context
Turn the raw documents in the in-folder into a prioritised, token-budgeted snapshot that later sessions load in one read.
Layout
.context/session/in/ immutable input: users drop documents here, no command edits it
.context/session/ctx/ generated snapshot: manifest, copies, summaries
.context/session/CONTEXT-baseline-llm.md single load point, 2000 tokens at most
Mindset
- Use the in-folder as the source of truth. The manifest mirrors it faithfully.
- Keep the snapshot scoped to the session's open questions. Include only what shapes decisions.
- Keep one manifest per session. Two manifests in one folder leave load-context unable to choose.
- State the origin of every constraint, assumption and decision that enters the baseline.
When to Use
- Use it once per project when raw documents sit in the in-folder and no ctx snapshot exists.
- Use it with
--forceafter the source documents changed materially. - Use it when load-context reports a missing manifest.
When Not to Use
- Do not use it when the ctx snapshot is current. A rerun without
--forcestops, and--forcediscards existing summaries. - Do not use it when the in-folder is empty. There is nothing to scan.
- Do not use it to refresh one document. Update that summary and its manifest entry by hand.
- Use save-context instead to store live session state in a named stream.
Steps
- Guard the prerequisites. Stop on a missing in-folder, and stop on an existing ctx folder unless
--forcewas passed.
[ -d .context/session/in ] || { echo "No in-folder found. Add source files first." >&2; exit 1; }
[ -d .context/session/ctx ] && [ "$ARGUMENTS" != "--force" ] && { echo "ctx exists. Use --force." >&2; exit 1; }
- Scan the in-folder with the bundled script. It lists md, txt, csv, yaml, yml and json files with a token estimate, and skips sensitive paths.
./scripts/scan-in-folder.sh .context/session/in
What ships with it
30 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/2026-04-11/analysis.md 1.2 KB
- .audits/2026-04-11/audit.json 487 B
- .audits/2026-04-11/remediation-plan.md 3.6 KB
- .audits/2026-09-23/Analysis.md 650 B
- .audits/2026-09-23/audit.json 843 B
- .audits/2026-09-23/Remediation.md 1.8 KB
- .audits/2026-10-07/Analysis.md 485 B
- .audits/2026-10-07/audit.json 547 B
- .audits/2026-10-07/Remediation.md 1.1 KB
- .audits/latest 10 B
- .tekhne/plugin.json 246 B
- CHANGELOG.md 323 B
- evals/instructions.json 2.9 KB
- evals/scenario-1/capability.txt 130 B
- evals/scenario-1/criteria.json 1.6 KB
- evals/scenario-1/task.md 306 B
- evals/scenario-2/capability.txt 139 B
- evals/scenario-2/criteria.json 1.0 KB
- evals/scenario-2/task.md 309 B
- evals/scenario-3/capability.txt 126 B
- evals/scenario-3/criteria.json 1.0 KB
- evals/scenario-3/task.md 271 B
- evals/scenario-4/capability.txt 135 B
- evals/scenario-4/criteria.json 1.0 KB
- evals/scenario-4/task.md 302 B
- evals/summary.json 656 B
- references/examples.md 2.5 KB
- references/reference.md 4.6 KB
- scripts/scan-in-folder.sh 2.4 KB runs code
- scripts/validate-manifest.sh 3.9 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.
- 10d ago Changed · -61 lines · +16 tokens per session 50ac2d201b8f
- 24d ago Changed · +30 lines aa87eacb608f
- 1mo ago First seen · 144 lines · 60 tokens per session scan A 9fbe0a9d7553
create-context is a skill published in the GitHub repository pantheon-org/tekhne (10 stars, last pushed today), licensed MIT. It adds 76 tokens to every session and 1,331 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-08-31.
Other skills, from other repositories
context-engineering
Optimizes agent context setup. Use when starting a new session, when agent output quality degrades, when switching between tasks, or when you need to configure rules files and context for a project.
comet-memory
A review step for deciding whether information should become durable personal memory. It can keep, update, forget, or skip memory candidates based on bounded evidence.
relevance-coarse-filter
Cheap, high-recall first-pass filter that removes obvious junk from a detector candidate pool before expensive story-origin research and PR judgment. Decides keep, monitoronly, or reject — never ranks, writes angles, verifies dates, or decides whether to pitch.
recall-memory
Recall relevant long-term memories on demand. Given a topic or question, judges relevance from pre-loaded metadata, loads only relevant files, and returns a concise summary to the main agent.
immune
Hybrid adaptive memory: Cheatsheet (positive patterns pre-generation) and Immune (negative patterns post-generation) with Hot/Cold tiered auto-learning. Triggers on: "scan for errors", "immune scan", "check output quality", "antibody scan". NOT for PR review (use pr-review) or repo audits (use repo-sentinel).
catchup
Rebuild the human's lost context on a project from live state, in plain language: what needs them, what changed, what new words mean. Use when the human returns after a gap, says they can't follow the project anymore, asks what happened or what a term means, or before deciding what to do next when their mental model…