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/tonydzi/second-brain-starter-kit/declinednpx skills add tonydzi/second-brain-starter-kit --skill declinedgit clone --depth 1 https://github.com/tonydzi/second-brain-starter-kitWrote 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/tonydzi/second-brain-starter-kit/declined)<a href="https://agentmods.dev/skills/tonydzi/second-brain-starter-kit/declined"><img src="https://agentmods.dev/badge/skills/tonydzi/second-brain-starter-kit/declined.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 | $0.00070 | $0.00852 |
| Opus 5 | $0.00035 | $0.00426 |
| Sonnet 5 | $0.00014 | $0.00170 |
| Haiku 4.5 | $0.00007 | $0.00085 |
Grade A, and why
declined 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 4d 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
OBJECTIVE: Show the registry of declined/deferred decisions (what · why · revisit-if) BEFORE (re-)pitching an idea — the anti "step on the same rake twice" guard. READ-ONLY: it writes nothing into the registry (the nightly scan and the human do that).
CONTEXT:
- The canonical registry (this hub):
%USERPROFILE%\.claude\projects\<hub-project>\memory\declined-decisions.md(a copy exists in the laptop project — always read the hub one). - The nightly detector:
$IMPORTS_ROOT/declined-scan/declined_scan.py(scheduled task "Declined-Decisions Nightly Scan", ~03:45) — it catches new refusals from fresh sessions and parks them on the AUTO-CAPTURED shelf. - The rule (cross-actor): rejected or deferred a proposal → record it in the registry. The canon for human assistants lives in the Bible as the "record a rejected decision" rule.
STEPS:
- Read
declined-decisions.md(the hub path above). 1b. Dead-man check on the watchdog (added 2026-07-04; catches the class "the task was silently disabled", as happened 06-22→06-27): read$IMPORTS_ROOT/declined-scan/highwater.json→ ifupdatedis older than 2 days the nightly watchdog is NOT running → check(Get-ScheduledTask -TaskName 'Declined-Decisions Nightly Scan').State, enable it (Enable-ScheduledTask), and report in one line. Fresh → move on silently. - If the operator asked about a SPECIFIC topic — grep the registry for it and show the matches (what was rejected · why · under what condition to revisit).
- Otherwise — a short summary: how many entries, the most recent additions, and the AUTO-CAPTURED shelf (waiting for promotion).
- (Optional, on "run the scan") execute
python $IMPORTS_ROOT/declined-scan/declined_scan.pyand show the newly caught refusals. - If the idea being pitched right now is ALREADY in the registry — warn the operator explicitly ("this was declined on , reason X, revisit if Y") before going further.
OUTPUT: a short list of relevant refusals, or a registry summary. It writes NOTHING (except step 4, where the scan writes for itself). Finish the reply to a non-technical operator with an "In plain words" recap.
RELATION (do not duplicate): the source registry = memory [[declined-decisions]]; the nightly scan = declined_scan.py; the rule for humans = the Bible entry on recording rejected decisions.
About & contact
Built and battle-tested at Palo Alto AI Research Lab — a fleet of Claude Code machines running 24/7 as a second brain and synthetic cofounder. Every skill here survived real production use before publication.
- 📦 All 101 skills: https://github.com/tonydzi/second-brain-starter-kit
- 👤 Author: Anton Dziatkovskii — Telegram @tonydzi · WhatsApp +1 341 222 9178 · X @Tony_Stef_
- 🧪 Engineers: want to test-drive this setup? Message me — I hand out free starter seeds to engineers who test and report back. Custom skill requests welcome.
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.
- 4d ago First seen · 43 lines · 70 tokens per session scan A ff0ac377d484
declined is a skill published in the GitHub repository tonydzi/second-brain-starter-kit (5 stars, last pushed 5d ago), licensed MIT. It adds 70 tokens to every session and 852 once invoked, about $0.0003 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
wiki-ingest
Ingest supplied source material into an Obsidian vault with provenance and claim tracking: pasted text, files staged in the selected vault's inbox or .raw archive, or explicitly approved URLs. Use for a single source or bounded batch, not for saving an assistant answer. Triggers: ingest, ingest this file, ingest this…
autoresearch
Run a bounded, source-grounded research loop, draft a cited dossier, and optionally propose a separately reviewed canonical vault merge. Use when the user wants autonomous or deep research that may access the public web. Triggers: /autoresearch, autoresearch, research this topic, deep dive into, investigate, find…
canvas
Create, inspect, and update Obsidian JSON Canvas boards with text, file, link, group, and edge nodes. Use for canvas status, canvas lists, visual maps, zones, spatial layouts, adding vault notes or media to a .canvas file, and requests such as create canvas, add to canvas, or put this on the canvas.
wiki-retrieve
Build and query a vault-local contextual BM25 retrieval index with optional multilingual Nomic cosine reranking; use for retrieve, hybrid retrieval, BM25, rerank, contextual retrieval, chunk search, vault search, semantic search, find relevant passages, or retrieval diagnostics. Derived caches stay under .vault-meta…
wiki
Initialize, adopt, and route work for a separate Obsidian knowledge vault through the portable claude-obsidian core. Use for vault setup, scaffolding, workspace selection, cross-project configuration, or choosing the correct wiki sub-skill. Triggers: /wiki, set up wiki, scaffold vault, create knowledge base, adopt…
defuddle
Plan and, with explicit network consent, use an optional external Defuddle cleaner to extract article-like HTTPS pages as Markdown. Use for defuddle, clean this URL, strip page clutter, readable Markdown from a web page, or preparing a web source for later wiki ingestion.