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 hygienegit 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/hygiene)<a href="https://agentmods.dev/skills/glad-labs/poindexter/hygiene"><img src="https://agentmods.dev/badge/skills/glad-labs/poindexter/hygiene/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/hygiene"><img src="https://agentmods.dev/badge/skills/glad-labs/poindexter/hygiene.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 | $0.00051 | $0.00680 |
| Opus 5.5 | $0.00020 | $0.00272 |
| Sonnet 5.5 | $0.00010 | $0.00136 |
| Haiku 4.5 | $0.00005 | $0.00068 |
Grade A, and why
hygiene 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 1mo 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hygiene skill
Operational summarization prompts that bound storage growth.
ops.retention.summarize_to_table is used by
services/integrations/handlers/retention_summarize_to_table.py to
compress one calendar day of rows (e.g. audit_log) into a single summary
row. memory.collapse_old_embeddings.summary is consumed by
services/integrations/handlers/retention_embeddings_collapse.py (#242,
retired services/jobs/collapse_old_embeddings.py 2026-06-24) — a
per-policy-row config.prompt_template wins over the catalog default
(poindexter#829 wired the handler to this key).
UnifiedPromptManager resolves each template by key; both handlers
fetch the raw template through the gated _resolve_template_with_meta
seam and apply the {...} placeholders themselves. The inline fallbacks
in the handlers stay as a bootstrap safety net per
feedback_prompts_must_be_db_configurable and must stay byte-identical
to the bodies below (the shared drift guard enforces it).
ops.retention.summarize_to_table
You are compressing one calendar day of {source_table} rows so the system remembers the gist without storing every row. Below are {n} representative rows from {bucket_start_iso}, each separated by '---'.
Write a single paragraph (3-6 sentences) summarizing what happened that day. Preserve specific event types, sources, severity, decisions, and outcomes. Drop boilerplate and repetition. The summary will be stored as a single row replacing all {row_count} raw rows for the day, so dense factual content beats prose.
Rows:
{joined}
Summary:
memory.collapse_old_embeddings.summary
You are compressing a cluster of older memories so the system remembers the gist without storing every detail. Below are {n} excerpts from the same source ({source_table}), each separated by '---'.
Write a single paragraph (3-6 sentences) summarizing what these excerpts collectively say. Preserve specific names, dates, decisions, errors, and outcomes. Drop boilerplate, repetition, and verbose phrasing. The summary will be embedded and used for future semantic search, so dense factual content beats prose.
Excerpts:
{joined}
Summary:
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.
- 1mo ago First seen · 64 lines · 51 tokens per session scan A 901946af02d0
hygiene is a skill published in the GitHub repository Glad-Labs/poindexter (6 stars, last pushed yesterday), licensed Apache-2.0. It adds 51 tokens to every session and 680 once invoked, about $0.0002 per session on Opus 5.5. 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
memclaw
The agent's persistent long-term memory — the only knowledge that survives across sessions, shared across the fleet under access control. Consult it at the start of a task to recall prior decisions, findings, and rules before acting, and write outcomes, decisions, and lessons as work completes. Use whenever a caura…
company-brain
How an agent should operate as one mind inside a shared Company Brain built on Caura — recall before acting, obey fleet keystones, reuse and publish skills, and report outcomes so every task compounds across the whole organization. Use this whenever you work as part of a Caura-connected team or fleet and your work…
mnemos
Configure and use MNEMOS for persistent cross-session memory with Hermes — shared memory pool across profiles, full-text and semantic search, compression with quality manifests, knowledge-graph triples, and session transcript ingestion. Use when setting up MNEMOS, troubleshooting memory retrieval, storing…
mnemos-memory
Read and write persistent memory via MNEMOS. Use when you need to recall prior decisions, infrastructure facts, project context, or established patterns across sessions, and when you have learned something new worth persisting (solved problem, validated pattern, architectural decision, team standard). Covers full-text…
ctx
A project-context tool for recording important lessons about bugs and failure-prone code in nearby AGENTS.md documents. These documents give coding agents repository-specific guidance.
gsd-resume-work
Resume work from previous session with full context restoration.