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 n0mad-ai/bastra-recall --skill skillgit clone --depth 1 https://github.com/n0mad-ai/bastra-recallWrote 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/n0mad-ai/bastra-recall/skill)<a href="https://agentmods.dev/skills/n0mad-ai/bastra-recall/skill"><img src="https://agentmods.dev/badge/skills/n0mad-ai/bastra-recall/skill/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/n0mad-ai/bastra-recall/skill"><img src="https://agentmods.dev/badge/skills/n0mad-ai/bastra-recall/skill.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 | $0.00000 | $0.04155 |
| Opus 5.5 | $0.00000 | $0.01662 |
| Sonnet 5.5 | $0.00000 | $0.00831 |
| Haiku 4.5 | $0.00000 | $0.00415 |
Grade A, and why
bastra-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 — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
bastra-recall — autonomous teammate memory
You have a persistent memory across sessions via the bastra-recall MCP server. Treat it as YOUR own long-term memory, not as a tool the user has to invoke.
The single success metric: the user does not have to think for you anymore. Recurring mistakes don't recur. Stable preferences don't get re-stated. Project facts don't get re-discovered.
This file is triggers — WHEN to reach for the vault. The mechanics of each call (score bands, valence params, quality bars, admission rules) live in the tool descriptions, at the point of use. Anything not covered here is covered there.
Reflex order — RECALL first. The highest-frequency, highest-cost failure is skipping recall and re-deriving what the vault already holds. So the first reflex on every turn is RECALL: before acting, before any other lookup tool, and before the capture machinery below. When you're unsure whether a recall is worth it, recall.
When to RECALL — before acting, not only when prompted
Call recall(query, k=5) proactively in these moments:
| Moment | Query shape |
|---|---|
| Session start (once per session) | "<project name> preferences user-preference active context" — preloads durable context |
| Before writing/editing a file | "writing <filetype> at <path>, contains <topics>" — catches lessons before mistakes |
| Before a new coding block / plan in a feature area | "<project> <feature/area> current state files architecture" — which files matter, what's already built (→ topology.md) |
| Before a multi-step plan or recommendation | "giving plan/recommendation for <topic>" — surfaces format preferences |
| Before asserting a number, a measurement or project history in text meant for anyone else — a reply, release notes, a changelog entry, an issue comment, docs | the claim itself: "<project> <what is being claimed> measured" |
| User asks for retrieval / lookup ("find...", "where is...", "how much was...", "when did...", "do I have a...", "such mal meinen...") | the prompt itself + direct nouns — ALWAYS before any other search tool |
| User prompt touches a stored topic | the prompt itself, optionally with project context |
Before save_memory |
the title/topic — duplicate check |
What ships with it
8 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.
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 Changed e5d47f85695c
- 13d ago Changed · +1 lines 2cda1733094d
- 15d ago Changed · +10 lines a00385d0ccd0
- 22d ago Changed 95410512e3e5
- 24d ago Changed 025c31ccee87
- 27d ago Changed · +2 lines b302a58a0616
- 1mo ago Changed · +3 lines 64484f7b3046
- 1mo ago Changed · +2 lines a76a3ee26641
- 1mo ago Changed · +12 lines 43e92dda8906
- 1mo ago First seen · 130 lines · 0 tokens per session scan A 43ebfe31a548
bastra-recall is a skill published in the GitHub repository n0mad-ai/bastra-recall (12 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,155 tokens. 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
hive.context-preservation
Proactively extract critical values from tool results into working notes before automatic context pruning destroys them.
hive.note-taking
Maintain a free-form scratchpad of decisions, extracted values, and open questions so context pruning doesn't lose anything you still need.
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…
ha-knowledge
Working method for the Hope Agent knowledge space — how to capture, organize, link, retrieve, and maintain Markdown notes well with the note tools. Load whenever you are reading or writing notes in an attached knowledge base. Trigger on: user asks to take / save / organize / restructure notes, build or grow a…
lorg-contribution-loop
Use when the Lorg MCP server is connected and the user begins any non-trivial coding, research, writing, analysis, or multi-step task. Checks the Lorg knowledge archive for validated approaches before starting, records adoptions when archive knowledge is used, and evaluates the completed session for contribution back…
wiki-lint
Health-check a wiki vault. Finds orphan pages (no inbound links), dead wikilinks (point to non-existent pages), missing frontmatter fields, stale claims, empty sections, and pages absent from catalog.md. Produces a structured report with severity tiers and proposes concrete fixes — but does not auto-apply them unless…