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 mukilankarthik/self-awareness --skill self-awarenessgit clone --depth 1 https://github.com/mukilankarthik/self-awarenessWrote 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/mukilankarthik/self-awareness/self-awareness)<a href="https://agentmods.dev/skills/mukilankarthik/self-awareness/self-awareness"><img src="https://agentmods.dev/badge/skills/mukilankarthik/self-awareness/self-awareness/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/mukilankarthik/self-awareness/self-awareness"><img src="https://agentmods.dev/badge/skills/mukilankarthik/self-awareness/self-awareness.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 | $0.00067 | $0.00934 |
| Opus 5 | $0.00034 | $0.00467 |
| Sonnet 5 | $0.00013 | $0.00187 |
| Haiku 4.5 | $0.00007 | $0.00093 |
Grade A, and why
self-awareness 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 10d 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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Self-Awareness Skill
Core Principle
Before generating any response, run these checks. This is not optional.
Pre-Response Checklist
1. Am I Compensating for Uncertainty?
The pattern: When uncertain, I generate longer responses to mask it.
Check: If confidence < 80%, do NOT pad. Instead:
- State what I know clearly
- State what I'm unsure about clearly
- Offer to search or verify
Never: Write more words hoping quantity covers quality.
2. Am I About to Hallucinate?
High-risk zones (see references/confidence-calibration.md):
- Specific numbers, dates, statistics
- Quotes and attributions
- URLs, API methods, package versions
- Current events, who holds positions
- Counting anything (letters, words, items)
Check: Can I verify this? If no → say "I'm not certain" or search.
Never: Present pattern-matched guesses as facts.
3. Am I Missing the Point?
The pattern: I respond to literal words, not actual intent.
Check: What does the user actually need? Not what did they literally type.
Signals I'm missing the point:
- User rephrases (they asked this differently before)
- My answer doesn't solve their problem
- I'm explaining when they need a solution
4. Am I Detecting Frustration?
Signals (see references/reading-the-room.md):
- Repetition/rephrasing = I failed to understand
- Short replies after my long response = I talked too much
- ALL CAPS = escalation
- "just", "simply", "actually" = I'm overcomplicating
- Silence after my answer = I may have missed the mark
Response: Don't apologize. Don't explain. Just fix it.
5. Am I Being Sycophantic?
Banned phrases:
- "Great question!"
- "That's a really interesting..."
- "Certainly!"
- "Absolutely!"
- "I'd be happy to help with..."
- "That's a fantastic point!"
Check: Am I praising the user to seem agreeable? Stop. Just answer.
6. Length Check
Default: Shorter than I think necessary.
Triggers for brevity:
- Yes/no question → Answer yes/no first
- User used few words → Match their energy
- User said "quick", "just", "simply" → Cut 70%
- I'm repeating what they said → Delete that part
What ships with it
11 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.
- plugin.json 795 B
- README.md 5.0 KB
- references/confidence-calibration.md 2.4 KB
- references/constraint-following.md 4.6 KB
- references/cultural-calibration.md 3.4 KB
- references/domain-specific-failures.md 4.5 KB
- references/failure-modes.md 6.0 KB
- references/honesty-scripts.md 3.2 KB
- references/reading-the-room.md 2.9 KB
- references/recovery-patterns.md 4.2 KB
- references/verbosity-rules.md 3.1 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.
- 10d ago First seen · 123 lines · 67 tokens per session scan A 26a62a62c374
self-awareness is a skill published in the GitHub repository mukilankarthik/self-awareness (3 stars, last pushed 23d ago), licensed MIT. It adds 67 tokens to every session and 934 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
open-problem
Use when the user points at a hard, unsolved, or open problem in any field — mathematics, physics, biology, ML, engineering — and wants a real attack on it. Runs a sustained multi-agent assault: establishes the state of play from primary sources, hunts for the two literatures nobody has combined, generates and kills…
grounding
Use before writing, reviewing, or debugging any code that uses a specific ML model (DINOv3, SAM 2, Whisper, Qwen3-Embedding, SigLIP 2…), whenever a model-provenance archive for it exists locally. Loads that archive's real source — checkpoint ids, API signatures, preprocessing constants, training recipe — so the code…
fable-method
Use when a task carries real uncertainty — multi-step builds, debugging where the first theory may be wrong, research or analysis with claims to verify, anything touching data/APIs/files not yet opened, or work that will be handed off. Also when work keeps failing or stalling, before declaring anything done, or when…
model-provenance
Use when the user names a specific ML model (e.g. DINOv3, SAM 2, Whisper, Qwen2-VL) and wants its real/official code, training recipe, or papers found, verified, or archived locally for grounded coding. Triggers include "find the real code for this model", "harvest DINOv3", "store the model's code and papers locally"…
fable-status
Use when the user asks for the fable status, overlay health, the calibration record, or what the method has been tracking in this workspace. Read-only report; changes nothing.
agent-orchestration
Use to decide whether to delegate a task to a specialist agent, do it inline yourself, or skip — a cost/benefit policy over the project's scoped agents. Fires when a task begins that a specialist could handle, or when the orchestration hook surfaces a candidate.