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 vault-capturegit 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/vault-capture)<a href="https://agentmods.dev/skills/pantheon-org/tekhne/vault-capture"><img src="https://agentmods.dev/badge/skills/pantheon-org/tekhne/vault-capture/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/vault-capture"><img src="https://agentmods.dev/badge/skills/pantheon-org/tekhne/vault-capture.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 | $0.00103 | $0.00692 |
| Opus 5 | $0.00051 | $0.00346 |
| Sonnet 5 | $0.00021 | $0.00138 |
| Haiku 4.5 | $0.00010 | $0.00069 |
Grade A, and why
vault-capture 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 8d 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
vault-capture
Persist a memory to the vault so it can be retrieved in future sessions.
Mindset
Before capturing, answer two questions:
- Is this time-bound? If yes →
episodic. If no, continue. - Is this a how-to process? If yes →
procedural. If no →semantic.
Always capture with --project when working in a project context. Always add
--tags with at least two relevant keywords — they are the primary BM25 signal
for future retrieval.
When to use
Use whenever the conversation produces:
- A confirmed decision ("we're using X instead of Y")
- A constraint that must not be violated
- A recurring bug or workaround
- A project convention or naming pattern
- A user preference expressed explicitly
How to use
vault-cli capture --text "<memory content>" [--tier episodic|semantic|procedural] [--project <id>] [--tags tag1,tag2]
Always double-quote the --text value to handle apostrophes and special characters.
Or pipe from stdin:
echo "<memory content>" | vault-cli capture
Tier selection
| Question | Answer | Tier |
|---|---|---|
| Is this tied to today's session or a specific event? | Yes | episodic (default) |
| Is this a rule, fact, or convention that should persist indefinitely? | Yes | semantic |
| Is this a step-by-step process or how-to? | Yes | procedural |
Examples
vault-cli capture --text "Decided to use Bun instead of Node for all scripts. Reason: workspace protocol support." --tier semantic --tags bun,tooling --project vault-core
vault-cli capture --text "Never use --force-push on main. CI enforces branch protection." --tier procedural --tags git,ci
vault-cli capture --text "Auth service fails silently when DB not ready — add depends_on with condition: service_healthy in docker-compose." --tier episodic --tags docker,auth,bug --project api
Never
- Never omit
--tierfor a rule or convention — defaulting toepisodicmeans it will decay and be consolidated away - Never capture without
--tags— untagged memories score poorly in BM25 retrieval - Never omit
--projectwhen working inside a project — global memories pollute cross-project searches - Never use single quotes around
--text— apostrophes in content will break the shell command
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.
- evals/instructions.json 2.6 KB
- evals/scenario-1/capability.txt 16 B
- evals/scenario-1/criteria.json 1.3 KB
- evals/scenario-1/task.md 379 B
- evals/scenario-2/capability.txt 15 B
- evals/scenario-2/criteria.json 1.2 KB
- evals/scenario-2/task.md 521 B
- evals/scenario-3/capability.txt 17 B
- evals/scenario-3/criteria.json 1.4 KB
- evals/scenario-3/task.md 435 B
- evals/scenario-4/capability.txt 17 B
- evals/scenario-4/criteria.json 1.1 KB
- evals/scenario-4/task.md 338 B
- evals/scenario-5/capability.txt 15 B
- evals/scenario-5/criteria.json 1.3 KB
- evals/scenario-5/task.md 317 B
- evals/summary_infeasible.json 58 B
- evals/summary.json 246 B
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.
- 8d ago First seen · 75 lines · 103 tokens per session scan A def31ac86290
vault-capture is a skill published in the GitHub repository pantheon-org/tekhne (10 stars, last pushed yesterday), licensed MIT. It adds 103 tokens to every session and 692 once invoked, about $0.0005 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 2026-08-31.
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.
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.
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.
self-improve
Extract lessons from the current session, or sweep the project's past sessions when asked, and route them to the appropriate knowledge layer (project AGENTS.md, auto memory, existing skills, or new skills). Use when the user asks to "self-improve", "distill this session", "distill past sessions", "sweep past…
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…