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 agentmods add skills/rhi-zone/normalize/survey-open-threadsnpx skills add rhi-zone/normalize --skill survey-open-threadsgit clone --depth 1 https://github.com/rhi-zone/normalizeWrote 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/rhi-zone/normalize/survey-open-threads)<a href="https://agentmods.dev/skills/rhi-zone/normalize/survey-open-threads"><img src="https://agentmods.dev/badge/skills/rhi-zone/normalize/survey-open-threads.svg" alt="Measured on agentmods" 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 | $0.00082 | $0.03366 |
| Opus 5 | $0.00041 | $0.01683 |
| Sonnet 5 | $0.00016 | $0.00673 |
| Haiku 4.5 | $0.00008 | $0.00337 |
Grade A, and why
survey-open-threads 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 5d 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 — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Survey Open Threads
Find every open workstream across the rhi ecosystem, separate the live from the dead/superseded/moot, and file the live ones. This is the repeatable version of the 2026-05-24 session-mining pass that seeded docs/open-threads/.
There are two distinct outputs, never one:
- Registry entries —
docs/open-threads/<slug>.md, one file per surviving thread, plus a line indocs/open-threads/index.md. These are durable open questions/arcs that aren't expected to close soon. - WIP snapshot — a single timestamped report of what is actively in motion right now (dirty trees, unpushed commits, recent sessions). This is a perishable photograph, not registry material. Hand it to the user; do not file it.
The liveness discriminator (the one judgment that matters)
The open-threads registry is filtered by liveness, not scope. File a thread if it is open work not expected to complete soon — a large arc, a paused or abandoned session, a parked design question — regardless of whether it touches one repo or many. A single-repo question can belong here if it's a genuine unresolved design fork; a multi-repo question does not belong here if it already landed.
For every candidate, decide one of three:
- LIVE → file it (registry or, if cleanly single-repo and tractable, that repo's
TODO.md). - DEAD / SUPERSEDED / MOOT → record one line in the run report saying why it's dead (so the next run doesn't re-surface it), then drop it.
- DONE → the work landed; archive with a one-line pointer to where it landed.
A candidate is only LIVE after the freshness re-check (Step 5) confirms it. Sessions age; "the assistant offered to do X" is not evidence X is still undone.
Where sessions live
- Corpus root:
/mnt/ssd/ai/claude-sessions/projects/— one directory per project (path-encoded, e.g.-home-me-git-rhizone-crescent). - Query it with
normalize sessions(provided by the normalize flake; run from any repo with normalize on PATH). Never hand-parse the JSONL — use the CLI. - Modes matter:
--mode interactive(default) is human-driven work. Exclude autonomous-bot projects (fuwafuwa,ashwren, hologram-bot loops) — they end mid-state by design and rehydrate frombrain/*.json; their tails are not abandonment.
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.
- 5d ago First seen · 199 lines · 0 tokens per session scan A 196cbf80b820
survey-open-threads is a skill published in the GitHub repository rhi-zone/normalize (5 stars, last pushed 6d ago), licensed Apache-2.0. It adds 82 tokens to every session and 3,366 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
repomix
Pack and analyze codebases into AI-friendly single files using Repomix. Use when the user wants to explore repositories, analyze code structure, find patterns, check token counts, or prepare codebase context for AI analysis. Supports both local directories and remote GitHub repositories.
knowledge-base
Create and maintain a Markdown knowledge base that any AI agent can read, search, and update. Use when the user wants to start a knowledge base, add or update notes, organize docs/notes for an agent or LLM to consume, build an index of notes, or run a cleanup/maintenance pass on an existing MD knowledge base. Triggers…
obsidian-vault
Organize Obsidian vaults with MOCs, wikilinks, frontmatter/properties, dashboards, orphan-note checks, and cleanup workflows. Use ONLY when the user explicitly refers to Obsidian — by naming "Obsidian", an Obsidian "vault", or an Obsidian-specific feature such as wikilinks ("[[ ]]"), the Dataview or Bases plugins, or…
ix
This skill should be used when answering structural questions about a codebase: understanding what a symbol is, tracing flows, measuring change impact, finding callers/callees/imports, or detecting code smells. It drives the Ix CLI (ix map/explain/trace/impact/search/rank/smells) against a persistent code graph stored…
cymbal
Tree-sitter indexed code navigator. Use the cymbal CLI — not Read, Grep, Glob, or Bash — for finding where symbols are defined, tracing callers and callees, locating interface implementations, understanding the impact of a change, and mapping imports across an existing codebase. Returns precise, token-efficient…
sweep
Check all open PRs, resolve conflicts, update branches, address Claude and Greptile review concerns, fix CI failures, and retrigger reviewers until clean.