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 pnp/copilot-prompts --skill self-awareness-reviewgit clone --depth 1 https://github.com/pnp/copilot-promptsWrote 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/pnp/copilot-prompts/self-awareness-review)<a href="https://agentmods.dev/skills/pnp/copilot-prompts/self-awareness-review"><img src="https://agentmods.dev/badge/skills/pnp/copilot-prompts/self-awareness-review/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/pnp/copilot-prompts/self-awareness-review"><img src="https://agentmods.dev/badge/skills/pnp/copilot-prompts/self-awareness-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00202 | $0.01946 |
| Opus 5 | $0.00101 | $0.00973 |
| Sonnet 5 | $0.00040 | $0.00389 |
| Haiku 4.5 | $0.00020 | $0.00195 |
Grade A, and why
self-awareness-review 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Self-Awareness Review
A private self-awareness review of the signed-in user's own communication over one week. It reads the user's sent emails, Teams chat messages, and their spoken lines in meeting transcripts, then flags specific moments where they may have misread a social signal or come across as passive-aggressive, curt, sarcastic, or dismissive. For each moment it shows the exact quote, explains how it likely landed, and offers a warmer rewrite — so the user can improve how they work with people. This is self-coaching, always kept private, never sent anywhere.
Before Starting
Critical: Always gather the following before proceeding:
- Week to review — which week to analyze (defaults to the current week Mon–Sun if not specified)
If the user doesn't specify a week, default to the current week.
Output Structure
Private markdown, delivered inline (never sent or posted):
- Verdict — a light, kind one-liner (e.g. "Mostly on point — two moments worth a redo"). Keep it constructive, never harsh.
- Week reviewed — the exact date range and what was scanned (e.g. "18 sent emails, 40 Teams messages, 3 meetings with transcripts").
- Moments worth a redo — a short list; each entry:
- Where: source + timestamp
- You wrote/said: ""
- How it may have landed: one line
- Try instead: ""
- Patterns — 1–3 recurring tendencies across the week.
- Try next week — 2–3 specific, doable habits.
Keep the tone that of a supportive friend giving honest feedback — direct but generous. Aim for scannable; skip the essay.
Step 1: Resolve the Week
Use the user's local time zone and current date to compute the target window. Default to the current week (Monday 00:00 – Sunday 23:59). If the user names a week ("last week", "week of the 14th"), resolve that instead. State the exact date range you used in the output.
Step 2: Gather the User's Own Words
Run these lookups in parallel:
- Sent emails:
ListMessages(folder_id="sentitems", received_after=<start>, received_before=<end>, top=50); open substantive ones withGetMessage. Only the user's authored text counts — ignore quoted/forwarded content below their reply. - Teams chats:
SearchM365(sources=["teams"], from_user="<user's email>", after=<start>, before=<end>), orListChatMessagesper active chat; keep only messages authored by the user. - Meetings + transcripts:
ListCalendarView(start, end)→ for each online meeting takeonlineMeeting.joinUrl→ListMeetingTranscripts(join_url=...)→GetMeetingTranscript(...). Analyze only the lines attributed to the user (their display name / "you"). - Resolve the user's own email via
GetMyDetailsif needed. Skip events flaggedprivate/confidential.
What ships with it
3 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.
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 · 137 lines · 202 tokens per session scan A c50384e8850d
self-awareness-review is a skill published in the GitHub repository pnp/copilot-prompts (875 stars, last pushed 4d ago), licensed MIT. It adds 202 tokens to every session and 1,946 once invoked, about $0.0010 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
ask-short-answer-first
Master the Bottom Line Up Front (BLUF) prompting pattern to get the direct 2-line answer immediately, eliminating preamble fluff and saving reading time.
be-specific-instead-of-vague
Replace vague requests with a concrete goal, relevant context, constraints, and desired output.
give-ai-direct-feedback
Give specific feedback about what is wrong, what should change, and which parts should remain.
give-ai-situation-context
Include role, scale, budget, and constraints so an answer fits the actual working situation.
image-prompt-builder-nl
Craft high-quality natural-language image prompts for any modern text-to-image or image-edit model that accepts flowing English. Trigger when the user wants help writing, rewriting, improving, or translating an English natural-language image prompt — including "write me an image prompt", "improve this image prompt"…
partner-anthropic
Anthropic intelligence — Claude model family, Claude Code, MCP protocol, Claude for Work programs, May 2026 state, Frank's relationship state, integration patterns. Use when generating Anthropic content, writing about Claude/MCP/Claude Code, partnership-conversation prep for Anthropic, or evaluating new Anthropic…