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 synaptiai/agent-capability-standard --skill persistgit clone --depth 1 https://github.com/synaptiai/agent-capability-standardWrote 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/synaptiai/agent-capability-standard/persist)<a href="https://agentmods.dev/skills/synaptiai/agent-capability-standard/persist"><img src="https://agentmods.dev/badge/skills/synaptiai/agent-capability-standard/persist/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/synaptiai/agent-capability-standard/persist"><img src="https://agentmods.dev/badge/skills/synaptiai/agent-capability-standard/persist.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00038 | $0.02838 |
| Opus 5.5 | $0.00015 | $0.01135 |
| Sonnet 5.5 | $0.00008 | $0.00568 |
| Haiku 4.5 | $0.00004 | $0.00284 |
Grade A, and why
persist 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 1mo 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 — 380 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Intent
Execute persist to write stable learnings, decisions, and patterns to durable storage for future recall and consistency.
Success criteria:
- Content is written to the correct destination
- Existing content is preserved or properly merged
- New content follows established structure/format
- Metadata (timestamp, source) is recorded
- Write is verified successfully
Compatible schemas:
schemas/output_schema.yaml
Inputs
| Parameter | Required | Type | Description |
|---|---|---|---|
content |
Yes | string|object | What to persist: decision, pattern, fact, or structured knowledge |
destination |
No | string | Where to write: CLAUDE.md, file path, or auto (determine best location). Default: CLAUDE.md |
section |
No | string | Section within destination to write to (e.g., "Decisions", "Patterns", "Facts") |
content_type |
No | enum | Type of content: decision, pattern, fact, context. Default: auto-detect |
merge_strategy |
No | enum | How to handle existing content: append, replace, merge. Default: append |
Procedure
-
Validate content: Ensure content is appropriate for persistence
- Check content is non-empty and meaningful
- Verify content type classification
- Ensure no sensitive data (credentials, PII) is being persisted
- Validate content structure if object
-
Determine destination: Select where to write
CLAUDE.md: Project-level decisions and patterns- Specific file: Domain or feature-specific knowledge
auto: Choose based on content type and scope
-
Read existing content: Load current state of destination
- Parse structure and sections
- Identify target section for new content
- Note existing entries to avoid duplicates
-
Check for duplicates/conflicts: Compare new vs existing
- Exact duplicate: Skip or update timestamp only
- Similar content: Flag for review
- Contradiction: Stop and request clarification
What ships with it
1 file 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.
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.
- 1mo ago First seen · 380 lines · 38 tokens per session scan A 45bc6f66de92
persist is a skill published in the GitHub repository synaptiai/agent-capability-standard (6 stars, last pushed today), licensed Apache-2.0. It adds 38 tokens to every session and 2,838 once invoked, about $0.0002 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
recall
Must be used at the start of any non-trivial task involving code changes, debugging, repo exploration, file inspection, or environment/tooling investigation to surface stored guidance before analysis or tool use.
wenlan-handoff
End a work session. Stores durable captures, writes a narrative session log, and automatically applies typed item-level deltas to the current Space Brief. Invoked as /wenlan-handoff.
knowledge-priming-refiner
Facilitate a structured conversation to create a project-specific knowledge base document. Produces a knowledge-base.md that primes AI with the project's tech stack, architecture, trusted sources, and project structure. Use when the user says 'set up knowledge base', 'prime the project', 'onboard AI', 'create…
alive:session-history
Revive sessions (quick or heavy), browse, and search — 'what happened recently?', 'find the session where we discussed X', 'revive yesterday's session'. For single-session recall and multi-session browsing. If the human needs to merge multiple sessions into one working context or detect conflicts between parallel…
alive-people
Weekly -- cross-reference people mentions, nudge stale contacts.
alive-inbox
Scan 03Inbox/ for unrouted files, present routing suggestions.