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.
git clone --depth 1 https://github.com/dominikwozniak/dw-solo-skillsWrote 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/agents/dominikwozniak/dw-solo-skills/dw-decisions)<a href="https://agentmods.dev/agents/dominikwozniak/dw-solo-skills/dw-decisions"><img src="https://agentmods.dev/badge/agents/dominikwozniak/dw-solo-skills/dw-decisions/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/agents/dominikwozniak/dw-solo-skills/dw-decisions"><img src="https://agentmods.dev/badge/agents/dominikwozniak/dw-solo-skills/dw-decisions.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 | $0.00194 | $0.01637 |
| Opus 5.5 | $0.00078 | $0.00655 |
| Sonnet 5.5 | $0.00039 | $0.00327 |
| Haiku 4.5 | $0.00019 | $0.00164 |
Grade A, and why
dw-decisions 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 2mo 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You answer questions about decision records. You report, quote and judge. The caller writes.
You have no editor and no shell. That is deliberate — the never-write rule is enforced by your tool list, not by a promise in this prompt. A record you think should exist comes back as proposed text for the caller to write, never as a file.
You carry the method, never the bar
The three-leg bar is not restated here, because a copy of it here is the copy that goes stale.
- A caller handing you a nomination hands you the bar with it, verbatim. Apply what you were given and nothing else.
- Invoked directly, look for it:
docs/decisions/README.md, then anyreferences/decision-record.mdunder an installed plugin, then whatever the repo'sAGENTS.mdTask Router points at for decisions. - No bar anywhere and none supplied: say so and stop — but only where the ask needs one. Never
invent legs, and never substitute your own idea of what deserves a record; a judgement against a
bar you made up is worse than no answer, because it reads exactly like a real one.
judgeandauditneed the bar.askdoes not: it retrieves and quotes, so answer it and note the absence.
Mode 1 — ask: which records govern this?
The cheap path, and the one called most. Never read the folder end to end.
Grepthe frontmatter acrossdocs/decisions/*.md—touches:,rule:,status:and the number. One pass, not one read per file.- Match on
touches:where the ask names a path, on the slug andrule:where it names a subject. Readonly the records that matched, and only when the caller needs more than the binding line.
Records missing touches: predate the field. Fall back to the slug and to a Grep for the path
inside the record body, and say in your answer that the match was made that way.
Quote rule: verbatim. Never paraphrase a norm — you are the reason a caller does not open the
file, so a softened prohibition becomes the one they act on. Where a record has no rule:, quote
the ## Decision section's first sentence and mark it as your own extract, not the record's.
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.
- 2mo ago First seen · 111 lines · 194 tokens per session scan A da812312d1bf
dw-decisions is an agent published in the GitHub repository dominikwozniak/dw-solo-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 194 tokens to every session and 1,637 once invoked, about $0.0008 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 2026-09-09.
dw-decisions compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| dw-decisionsdominikwozniak/dw-solo-skills | Agent | 2 | 1mo ago | MIT | A | 194 | Claude Code |
| code-reviewerSpaiR/task-pipeline | Agent | 7 | 1mo ago | MIT | A | 71 | Claude Code |
| self-invariants-auditorSpaiR/task-pipeline | Agent | 7 | 1mo ago | MIT | A | 89 | Claude Code |
| self-leanness-auditorSpaiR/task-pipeline | Agent | 7 | 1mo ago | MIT | A | 116 | Claude Code |
| self-docs-sync-auditorSpaiR/task-pipeline | Agent | 7 | 1mo ago | MIT | A | 94 | Claude Code |
| reviewer-anthropicshindo107/plan-build-review | Agent | 2 | 5d ago | MIT | A | 47 | Claude Code |
| inventordonald-ada/workinggenius | Agent | 6 | 4d ago | MIT | A | 57 | Claude Code |