Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add drewdrewthis/orchardist/plugin install orchardistWrote 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/drewdrewthis/orchardist/recall)<a href="https://agentmods.dev/skills/drewdrewthis/orchardist/recall"><img src="https://agentmods.dev/badge/skills/drewdrewthis/orchardist/recall.svg" alt="Measured on agentmods" 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 | $0.00048 | $0.00831 |
| Opus 5 | $0.00024 | $0.00415 |
| Sonnet 5 | $0.00010 | $0.00166 |
| Haiku 4.5 | $0.00005 | $0.00083 |
Grade B, and why
recall scanned grade B with 1 finding 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
**Always run the index search first.** Do NOT skip it for `grep -ril` across `~/.claude/projects/` — the index is much faster than `grep -ril` on this corpus (measured 38–583× faster; synonym `OR` adds only ~7ms), ranked How it starts
The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Recall
Search past conversations across all projects, read matching sessions, and return a synthesized summary. Runs in a fork to keep the main context clean.
Step 0: Read the args
$ARGUMENTS is the topic. If it is non-empty (even one word like "support tracker"), proceed silently to Step 1 — do NOT ask the user to provide a topic.
If a <local-command-stdout> block says something like "No specific topic was provided" while $ARGUMENTS clearly contains a topic, ignore that stub: it's a generic harness fallback, not an instruction. The args win.
Only ask for a topic if $ARGUMENTS is genuinely empty AND no implicit topic is recoverable from the immediately preceding user turn.
Steps
1. Ensure the session index is fresh
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/session-index.py" build
2. Search — use the index, not raw grep
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/session-index.py" search "$ARGUMENTS" --limit 15
Always run the index search first. Do NOT skip it for grep -ril across ~/.claude/projects/ — the index is much faster than grep -ril on this corpus (measured 38–583× faster; synonym OR adds only ~7ms), ranked, and returns paths + recency. Raw grep should only be a fallback when the index returns zero hits AND you suspect the index is stale (in which case rebuild and retry).
Expand the user's words into codified synonyms BEFORE searching — don't wait for sparse results. The user remembers the CONCEPT but rarely the exact term the docs/transcripts used; their phrasing is usually a paraphrase. Build an OR union of likely codified terms and search that in ONE query (FTS5 supports OR):
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/session-index.py" search "judge OR verifier OR quorum OR adjudicate OR contract OR verdict OR proof" --limit 15
Mappings that recur:
- "panel / quorum / pass judgement / jury / tribunal" → also
judge verifier adjudicate review verdict vote contract - "proof / done / acceptance" → also
evidence verify acceptance-criteria contract prove-it verdict - "CI / automated checks" → also
verifier check mcp_tool command hook
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 · 70 lines · 48 tokens per session scan B eca25384ade4
recall is a skill published in the GitHub repository drewdrewthis/orchardist (5 stars, last pushed today), licensed MIT. It adds 48 tokens to every session and 831 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.