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 DustinVK/wherefore --skill capturegit clone --depth 1 https://github.com/DustinVK/whereforeWrote 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/dustinvk/wherefore/capture)<a href="https://agentmods.dev/skills/dustinvk/wherefore/capture"><img src="https://agentmods.dev/badge/skills/dustinvk/wherefore/capture/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/dustinvk/wherefore/capture"><img src="https://agentmods.dev/badge/skills/dustinvk/wherefore/capture.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 | $0.00118 | $0.03259 |
| Opus 5.5 | $0.00047 | $0.01304 |
| Sonnet 5.5 | $0.00024 | $0.00652 |
| Haiku 4.5 | $0.00012 | $0.00326 |
Grade A, and why
capture 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 — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Wherefore: capture
Turn a raw or AI-generated discussion into one compact, retrievable wherefore entry. Preserve the useful residue (what was decided, why, and what was rejected), not a transcript. Months later, someone asking "why did we build it this way?" should get the answer in a few sentences.
No em dashes. Periods, commas, colons, semicolons, or parentheses instead. Firm project rule.
Never delete anything under a wherefore/ data dir. Retire, do not delete.
Writing style
The record must read well as a raw markdown file, not just in the dashboard. Editors and the GitHub blob view are where most people read it.
- No em dashes anywhere. Use periods, commas, colons, semicolons, or parentheses. Firm project rule.
- Decisions are verdict-led. Open each bullet with the ruling as a short standalone clause; put elaboration after it or in Why. Someone reading only the first clause of every bullet should still get the full outcome.
- One decision per bullet. Split compound bullets.
- Do not use inline bold to fake structure. The lead clause carries the scan. Bold scattered mid-sentence is the main cause of wall-of-text records. Reserve emphasis for a rare load-bearing term.
- Keep sentences short and concrete.
- Why is the single home for rationale. State the outcome in Decisions, the reasoning in Why. Do not scatter reasoning across decision bullets.
- Unresolved threads are not decisions. They go to Open questions and become a numbered question (
Q-NNNid, in aQ-NNN-short-slug.mdfile), never a Decisions bullet dressed as certainty.
Verdict-led, in practice:
- Weak: "There are two fulfillment paths, direct and via inventory, and after weighing platform fit we lean toward starting inventory-based and moving to direct later."
- Strong: "Start inventory-based, move to direct later. Two paths exist: direct (seller ships to buyer) and via inventory (trader stocks, then ships)."
Storage layout
All entries live under a repo-relative wherefore/ directory:
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.
- 1mo ago First seen · 201 lines · 118 tokens per session scan A cd692516ec45
capture is a skill published in the GitHub repository DustinVK/wherefore (1 stars, last pushed 3mo ago), licensed MIT. It adds 118 tokens to every session and 3,259 once invoked, about $0.0005 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
decision-memory
Use when planning, designing, reviewing, or changing code in a repository that keeps ADRs (usually docs/adr) — to load the decisions that already govern the work, check a plan or diff against them, or record a new decision. Also use when a choice feels already-settled and you cannot find where it was settled.
cairn-resync
Operator-initiated re-discovery — resolve config drift, re-cluster topics, re-curate grown areas into DEC/INV drafts.
rosetta
Reconcile ALL prior agent conversations (Claude Code, Codex, Droid/Factory, Hermes, Cursor) with git history and docs into a cited ground truth, and distill durable decision records (ADRs/PDRs/BDRs). Use whenever the user wants to catch up on or get the state of a project, build or refresh a ground truth, read or mine…
weekly-digests
Generate a serial week-by-week narrative digest of a project's full claude-mem timeline. Splits the timeline into per-ISO-week files, then runs one consecutive subagent per week — each receiving the prior week's carry-forward block — to produce one chapter per ISO week of data. Use when asked for "weekly digests"…
cloud-sync
Set up or check claude-mem cloud sync with cmem.ai Pro. Use when the user says "set up cloud sync", "sync my memories", "cmem pro", "cloud backup", "sync status", or wants their memory database backed up or synced to their cmem.ai account.
long-context
Extend context windows of transformer models using RoPE, YaRN, ALiBi, and position interpolation techniques. Use when processing long documents (32k-128k+ tokens), extending pre-trained models beyond original context limits, or implementing efficient positional encodings. Covers rotary embeddings, attention biases…