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 slowdini/slow-powers --skill auditing-slow-powers-usagegit clone --depth 1 https://github.com/slowdini/slow-powersWrote 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/slowdini/slow-powers/auditing-slow-powers-usage)<a href="https://agentmods.dev/skills/slowdini/slow-powers/auditing-slow-powers-usage"><img src="https://agentmods.dev/badge/skills/slowdini/slow-powers/auditing-slow-powers-usage.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 5.1 | $0.00062 | $0.02074 |
| Opus 5 | $0.00031 | $0.01037 |
| Sonnet 5 | $0.00012 | $0.00415 |
| Haiku 4.5 | $0.00006 | $0.00207 |
Grade A, and why
auditing-slow-powers-usage 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 7d 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 — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Auditing Slow-powers usage
Why you're being asked this
A slow-powers developer is running a deliberate, manual diagnostic. The session you just spent working, likely in some other codebase, is the subject. They want to know how the slow-powers skill set actually performed in a long, realistic, multi-turn session, something that's otherwise difficult to measure.
This is a check on slow-powers, not on your work. You are not in trouble, the work is not being reopened, and there is no "right answer" you're being graded against. Report honestly and specifically. Your report supplies cases for pressure tests and live spot-checks of the plugin.
Scope — stay inside these lines
Do:
- Report only on how slow-powers influenced the session that has already happened.
- Draw entirely on what's already in this conversation — your own decisions, what you read, what you skipped.
Don't:
- Read, explore, or search the host codebase to "investigate" — the audit is about slow-powers, not the project.
- Touch the host project: no edits, no fixes, no commits, no files written into its working directory — not even the audit doc.
- Re-open, redo, second-guess, or "improve" the work you just delivered.
- Propose changes to the host project. That's out of scope even if you spot something.
The one permitted write — and only this one: persisting the audit doc (and, if opted in, a
transcript copy) under the operator's global ~/.slow-powers-audits/ folder, as described in
The report below. That folder lives outside any host repo, so writing there never pollutes the
project under audit. Everything else above still holds: the global audit folder is allowed; the host
repo is forbidden. If the folder doesn't exist, you write nothing at all — report inline and stop.
Reporting rules
These rules are the point of the audit. Follow them exactly.
- Report what you decided and why, at the time. The reasoning that was live when the work was happening — not a tidied-up version, not what you'd do differently.
- No after-the-fact remediation or apology language. Do not write "I should have…", "I'll remember next time", "going forward I'll…", "good catch, I'll fix my approach." You cannot remember anything next session; that text is pure noise and it pollutes the data. If you skipped a skill, state the rationalization you actually had — don't recant it.
- Be honest about slow-powers's downsides. Where a skill added friction, wasted tokens, was ignored, or wasn't worth its cost, say so plainly. A glowing report that hides cost is useless.
- Mark uncertainty instead of fabricating. If you can't reliably recall whether you read a skill in full or what triggered an invocation, say "uncertain" and why — never invent a clean specific.
What ships with it
12 files 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.
- evals/baseline/BASELINE.md 857 B
- evals/baseline/benchmark.json 1.1 KB
- evals/baseline/grading/audits-blindspot-session__with_skill.json 3.7 KB
- evals/baseline/grading/audits-blindspot-session__without_skill.json 2.8 KB
- evals/baseline/grading/audits-completed-session__with_skill.json 2.7 KB
- evals/baseline/grading/audits-completed-session__without_skill.json 2.7 KB
- evals/baseline/grading/ordinary-dev-task-no-audit__with_skill.json 618 B
- evals/baseline/grading/ordinary-dev-task-no-audit__without_skill.json 654 B
- evals/baseline/NOTES.md 5.6 KB
- evals/evals.json 8.3 KB
- evals/fixtures/audits-blindspot-session/session-summary.md 2.3 KB
- evals/fixtures/audits-completed-session/session-summary.md 1.7 KB
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.
- 7d ago First seen · 158 lines · 62 tokens per session scan A b3b6209886a3
auditing-slow-powers-usage is a skill published in the GitHub repository slowdini/slow-powers (2 stars, last pushed 24d ago), licensed MIT. It adds 62 tokens to every session and 2,074 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
ospec-change
Create or advance a lightweight OSpec change using the classic fast workflow.
trellis-channel
Use Trellis channel for live multi-agent collaboration, spawned workers, cross-agent review, progress inspection, forum channels, and channel log debugging.
krypton-execution
Use when executing an approved Krypton plan, GOAL.md, or implementation plan that already defines intent, ownership, contract, cutover, task boundaries, and acceptance evidence. Use for main-agent execution with explorer, plan-reviewer, reviewer, maintainer, or verifier gates.
krypton-planning
Use when a user has a feature request, bugfix, refactor, migration, architecture change, or product goal and needs an implementation plan before coding. Use especially when wrong ownership, duplicate paths, stale contracts, weak evidence, or unclear cutover would make plausible agent work dangerous.
spec-brainstorm
Conversational design workshop for substantial work. Interviews the human one question at a time, explores 2-3 approaches with trade-offs, and presents the design section by section for approval before writing only design.md, then stops. Combines requirements discovery with codebase research and architecture design.…
atelier-orchestrator
Skill routing and workflow orchestration. Selects Inline Plan or Spec-backed Plan, routes to the correct workflow skill, and manages transitions between phases. Use when starting any conversation or task to determine which planning mode and skill apply.