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 jolliai/jolli-claude-plugin --skill recallgit clone --depth 1 https://github.com/jolliai/jolli-claude-pluginWrote 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/jolliai/jolli-claude-plugin/recall)<a href="https://agentmods.dev/skills/jolliai/jolli-claude-plugin/recall"><img src="https://agentmods.dev/badge/skills/jolliai/jolli-claude-plugin/recall/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/jolliai/jolli-claude-plugin/recall"><img src="https://agentmods.dev/badge/skills/jolliai/jolli-claude-plugin/recall.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 | $0.00052 | $0.00711 |
| Opus 5 | $0.00026 | $0.00356 |
| Sonnet 5 | $0.00010 | $0.00142 |
| Haiku 4.5 | $0.00005 | $0.00071 |
Grade A, and why
recall 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 12d 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.
This is a copy
100% identical to recall — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Jolli Recall
Every commit deserves a Memory. Every memory deserves a Recall.
Load the structured development context for a branch — commits with their distilled topics (trigger / response / decisions / files), plus any plans and notes the work referenced — and synthesize a grounded answer to the user's prompt about that branch.
Step 1: Load the recall result
<user-arg> is a branch name (exact or fragment) or empty (current branch).
Preferred — MCP tool. If the recall tool from the jollimemory MCP
server is available, call it with { "branch": "<user-arg>" } (omit branch
when <user-arg> is empty). It returns a type-tagged object
(recall / catalog / error).
Fallback — bundled CLI. If the MCP tool is unavailable, run the Jolli CLI
through its stable dispatch script. Pass the argument via here-doc so it can
never be interpreted as shell — do NOT interpolate <user-arg> into argv or a
quoted string.
Generate a fresh random 16-character hex string (the "delimiter token") for
this invocation — e.g. 3f8a9b2c5d7e1f4a — and replace the two <DELIM>
occurrences below with it. Quickly scan the user's argument: if it contains a
line that is exactly JOLLI_ARG_<delimiter token>_END, regenerate the token
and re-check. A per-invocation random delimiter is what makes a pre-computed
prompt-injection payload (a line that closes the here-doc early to smuggle
shell) useless — do NOT hardcode a fixed delimiter.
JOLLI_INVOKED_VIA=skill:recall "$HOME/.jolli/jollimemory/run-cli" recall --arg-stdin --format json <<'JOLLI_ARG_<DELIM>_END'
<user-arg>
JOLLI_ARG_<DELIM>_END
Step 2: Handle the result by type
type:"recall"→ render the branch facts (branch,period,commitCount) then walkcommits[](each hashash,commitMessage,recap?, andtopics[]with always-presenttitle+decisions). Surface decisions prominently; they are never dropped from a kept commit.type:"catalog"→ semantic-match<user-arg>against the listed branches; one match → repeat Step 1 with it, many → list and ask, none → show catalog.type:"error"→ surfacemessageverbatim. For "no records": if the user is not signed in to Jolli (see/jolli:status), note that memories are only generated once signed in and suggest/jolli:login(no Anthropic API key needed); otherwise suggest committing some work first so Jolli can generate memories.
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.
- 12d ago First seen · 56 lines · 52 tokens per session scan A a0ff7a5d7592
recall is a skill published in the GitHub repository jolliai/jolli-claude-plugin (2 stars, last pushed 14d ago), licensed Apache-2.0. It adds 52 tokens to every session and 711 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to recall, differing in 0 lines, and is treated as a copy.
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.