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 gnurio/nurijanian-skills --skill decision-auditgit clone --depth 1 https://github.com/gnurio/nurijanian-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/skills/gnurio/nurijanian-skills/decision-audit)<a href="https://agentmods.dev/skills/gnurio/nurijanian-skills/decision-audit"><img src="https://agentmods.dev/badge/skills/gnurio/nurijanian-skills/decision-audit/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/gnurio/nurijanian-skills/decision-audit"><img src="https://agentmods.dev/badge/skills/gnurio/nurijanian-skills/decision-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Memory Poisoning · line 27 Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.Fix: Protect agent memory and state from modification by untrusted content. Use read-only memory for critical instructions and validate all state changes.
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 | $0.00174 | $0.01524 |
| Opus 5 | $0.00087 | $0.00762 |
| Sonnet 5 | $0.00035 | $0.00305 |
| Haiku 4.5 | $0.00017 | $0.00152 |
Grade A, and why
decision-audit 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 12d 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 — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Decision Audit
Read references/pm-excellence-behaviors.md before beginning. Focus on Cluster 2 (Decision Quality)
as the primary lens, with Clusters 1, 3, and 6 as secondary lenses for how the decision was made
and communicated.
What This Mode Does
The PM describes a decision they made. You walk them through a structured audit of the decision process — not whether it worked out, but whether it was made with the rigor, transparency, and customer-centricity that defines excellent PM decision-making.
The output is a decision quality scorecard and a clear statement of where the process fell short.
Process
Step 1: Get the Decision
Ask the PM to describe the decision. You need:
- What was decided? (feature cut, priority change, direction call, scope trade-off, etc.)
- When? (recent enough that details are fresh)
- What was the alternative? (every decision has a road not taken — what was it?)
- What happened? (outcome so far, if any)
If they've already described it, work with what you have.
Step 2: The Audit Interview
Ask these questions one at a time. Don't ask all of them at once — listen and adjust based on what they say:
On data and grounding: "What data or research informed this decision? Walk me through what you looked at."
On the customer: "Where does the customer appear in the reasoning? How did user impact factor into the call?"
On alternatives: "What was the strongest argument for the alternative you didn't choose? Did you seriously consider it?"
On transparency: "How did you communicate the decision to the team? Did you share the 'why' or just the 'what'?"
On reversibility: "Was this a reversible or irreversible decision? Did you treat it accordingly — i.e., move fast on reversible, slow down on irreversible?"
On pressure: "Was there any external pressure (leadership, timeline, politics) that shaped this decision? If so, how did you account for it?"
On dissent: "Did anyone push back? If so, what happened to that pushback?"
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.
- 12d ago First seen · 148 lines · 174 tokens per session scan A b127c66a4b25
decision-audit is a skill published in the GitHub repository gnurio/nurijanian-skills (107 stars, last pushed 29d ago), licensed MIT. It adds 174 tokens to every session and 1,524 once invoked, about $0.0009 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 2026-08-30.
Other skills, from other repositories
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
story-readiness
Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…
magpie-security-issue-import-from-md
Open one or more tracking issues from a markdown file containing a batch of security findings. Each finding becomes one tracker landing in the Needs triage board column. The file itself is the full report — there is no inbound reporter to reply to and no PR to inspect.
remove
Remove a deployed framework or addon from the current workspace.