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 Glad-Labs/poindexter --skill recall-conversationgit clone --depth 1 https://github.com/Glad-Labs/poindexterWrote 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/glad-labs/poindexter/recall-conversation)<a href="https://agentmods.dev/skills/glad-labs/poindexter/recall-conversation"><img src="https://agentmods.dev/badge/skills/glad-labs/poindexter/recall-conversation/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/glad-labs/poindexter/recall-conversation"><img src="https://agentmods.dev/badge/skills/glad-labs/poindexter/recall-conversation.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 | $0.00080 | $0.00453 |
| Opus 5 | $0.00040 | $0.00227 |
| Sonnet 5 | $0.00016 | $0.00091 |
| Haiku 4.5 | $0.00008 | $0.00045 |
Grade A, and why
recall-conversation 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 11d 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.
What it actually says
Recall Conversation
Slice 3 of the voice-agent rollout (Glad-Labs/poindexter#390). Wraps a
pgvector cosine search over the voice_messages table — the same query
the bot runs implicitly on every user turn — but exposed as an explicit
voice-invokable skill so the operator can also ask "what did I say
about X earlier?" without relying on the implicit recall surfacing it.
Backed by scripts/_voice_memory.recall_similar_turns() and direct
asyncpg access to voice_messages (no API hop — recall is local-only
data). Embedding via nomic-embed-text:768 against Ollama at
OLLAMA_URL / voice_agent_ollama_url.
Usage
scripts/run.sh "<topic>" [limit] [min_similarity]
Parameters
- topic (string, required): natural-language description of what to recall from the conversation transcript
- limit (int, optional, default
voice_agent_recall_kor 3): top-N prior turns to surface - min_similarity (float, optional, default
voice_agent_recall_min_similarityor 0.5): cosine-similarity floor
Output
One-line spoken summary listing the top hits with role + similarity + preview. Empty result is the no-match path (skill prints a friendly "nothing came up" line).
Example
> scripts/run.sh "the dashboard variety thing"
Found 2 prior turns. [0.78] user: I was talking about wanting more chart variety in the Grafana dashboards | [0.62] assistant: Mix of stats, gauges, time series, badges...
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.
- 11d ago First seen · 46 lines · 80 tokens per session scan A bd34fcb6f5a2
recall-conversation is a skill published in the GitHub repository Glad-Labs/poindexter (5 stars, last pushed today), licensed Apache-2.0. It adds 80 tokens to every session and 453 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
crawl4ai
AI-friendly web crawling and content extraction via Crawl4AI. Use when: (1) need to scrape web pages for AI consumption, (2) extract structured data from websites, (3) convert web content to clean Markdown, (4) build RAG knowledge bases from web sources. Preferred over basic fetch when pages have JS rendering or…
feishu-wiki
Feishu knowledge base navigation. Activate when user mentions knowledge base, wiki, or wiki links.
status
Use when the user wants a one-screen view of current hyperflow project state — version, profile freshness, memory count, and live progress on every in-flight task. Read-only; never modifies state, never dispatches workers. Trigger with /hyperflow:status, "what is hyperflow doing", "show task progress", "where are we".
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.
notes
Skill "notes" from Pinvou/pinvou-agent, covering ima notes, operations, write rules, examples and response handling.
exploiting-format-string-vulnerabilities
Methodology for exploiting format string bugs where attacker-controlled data reaches the format argument of printf-family functions, enabling stack/memory disclosure (info leaks for ASLR/PIE/canary defeat) and arbitrary write primitives (%n) to hijack control flow via GOT/.finiarray overwrites.