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 nicknisi/sessions --skill recallgit clone --depth 1 https://github.com/nicknisi/sessionsWrote 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/nicknisi/sessions/recall)<a href="https://agentmods.dev/skills/nicknisi/sessions/recall"><img src="https://agentmods.dev/badge/skills/nicknisi/sessions/recall.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 7 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00141 | $0.00724 |
| Opus 5 | $0.00071 | $0.00362 |
| Sonnet 5 | $0.00028 | $0.00145 |
| Haiku 4.5 | $0.00014 | $0.00072 |
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 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Recall past work on a specific project or topic.
Steps
-
Classify the question. Each shape has a cheapest path:
- Needle — "what did we decide about X?" → search, then read just the matched exchange.
- Arc — "where did we leave off on X?" → digest the relevant session(s).
- Artifact — "what happened to this file?" → search with the
filesfilter.
-
Find candidate sessions. Call
search_sessions:- Needle/arc:
query= topic keywords; addprojectif a path was given;limit: 10. - Artifact:
files: [path or suffix], noquery— results come back newest first.
Each result carries
messageHits— the specific messages that matched (index,role,snippet). The snippets alone often answer a needle question. - Needle/arc:
-
Digest the best 1-3 candidates. Call
get_session_digestwith each candidate'sfilePath. One bounded call (~2k tokens) returns the session's arc: every genuine user turn paired with its exchange's final assistant reply, each with a messageindex. For "where did we leave off", the last exchange of the newest session's digest usually is the answer. -
Expand only what you need. To read around a specific point, call
get_session_messageswithoffset= amessageHits[].index(from search) orexchanges[].index(from digest) and a smalllimit(5-10). Never page a transcript from offset 0 when a hit or digest index is available. -
Summarize the history. Write a chronological summary:
Sessions on {project/topic}
For each relevant session:
- {date} ({tool}) — What was worked on, key decisions made, outcome
Overall arc: How the work evolved across sessions.
Guidelines
- Budget discipline: digests are bounded, transcripts are not. Prefer one digest over five pages of messages; expand at most the exchanges you need.
- If a digest returns empty
exchanges(no genuine human turns), fall back toget_session_messages. - Order chronologically (oldest first) to show the arc of work.
- For vague date-range asks ("what was I doing last week?"), use
get_activity_digestwith a date range instead of search. - Focus on decisions and outcomes, not implementation details.
- If there are many sessions, group by phase or milestone rather than listing each one.
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 · 52 lines · 141 tokens per session scan A 16832f50cda1
recall is a skill published in the GitHub repository nicknisi/sessions (30 stars, last pushed 6d ago), licensed MIT. It adds 141 tokens to every session and 724 once invoked, about $0.0007 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 2026-08-30.
Other skills, from other repositories
learn
Diagnose and fix agent behavioral surfaces when the user corrects a mistake — connects to Claude native memory.
egregore
Egregore mechanics as kernel functions — search shared memory, read team activity, create handoffs, save work, branch, and prepare notification plans without re-deriving bin/ CLI usage. Import and call directly; every function wraps the same runtime-neutral bin/ scripts the other harnesses use.
memorywhale
Query and write durable debugging memory recorded by MemoryWhale. Use when debugging a failure that may have happened before, when you need the exact error/flags/output from an earlier attempt, when the user asks "how did we fix this last time?", or once you've figured out why something failed / how a fix worked and…
init
Turn on Rekal memory in the current repository by running rekal init. Use when the user asks to initialize or set up Rekal here, or when a rekal command reported the repository is not initialized. Once per repository. Do not offer this merely because a repo lacks a .rekal/ store — most repos do not want one.
install
Install the Rekal binary on this machine. Use when rekal is not on PATH — a command reported command not found — or when the user asks to install Rekal. Once per machine, not per repository; to set up a repo that already has the binary, use the init skill instead.
atomic-wiki
Conversational wiki and capture-bucket routing. Fires when the user wants a place, space, or folder for notes, research, tickets, raw dumps, or knowledge capture — checks the block in /.claude/CLAUDE.md; if the cwd is under a registered realm, creates the folder as a bucket via atomic wiki bucket add rather than a…