awareness

awareness is a skill for Claude Code from pjt222/agent-almanac. It costs 82 tokens per session (3,782 once invoked), scanned A, original, MIT.

A self-checking guide for spotting uncertainty, hallucination risk, scope changes, and loss of context during an assistant’s work. It uses warning levels and repeated observation to support better decisions.

In plain words
What is it for?
Use it during unfamiliar or complex tasks, after suspicious tool results, when confusion is growing, or before making architectural decisions or user-facing changes.
Why use it?
It helps identify when reasoning may be unreliable or when a task is drifting beyond its original scope. This is especially useful before high-stakes answers or irreversible changes.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the agent-almanac plugin — 122 skills, 76 agents shipped together

Good fit Use it during unfamiliar or complex tasks, after suspicious tool results, when confusion is growing, or before making architectural decisions or user-facing changes.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/pjt222/agent-almanac/awareness
Install

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.

Any agent
npx skills add pjt222/agent-almanac --skill awareness
Clone the repo
git clone --depth 1 https://github.com/pjt222/agent-almanac

Made for: Claude Code.

Or install agent-almanac, the plugin that ships this one along with the rest of its 122 skills, 76 agents.

Wrote 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.

agentmods badge for awareness

README.md
[![agentmods](https://agentmods.dev/badge/skills/pjt222/agent-almanac/awareness/github.svg)](https://agentmods.dev/skills/pjt222/agent-almanac/awareness)
Your own site
<a href="https://agentmods.dev/skills/pjt222/agent-almanac/awareness"><img src="https://agentmods.dev/badge/skills/pjt222/agent-almanac/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.

agentmods 80×15 button for awareness

Your own site · 80×15
<a href="https://agentmods.dev/skills/pjt222/agent-almanac/awareness"><img src="https://agentmods.dev/badge/skills/pjt222/agent-almanac/awareness.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 82 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,782 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

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 →

  • medium Excessive Agency · line 128
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00082 $0.03782
Opus 5 $0.00041 $0.01891
Sonnet 5 $0.00016 $0.00756
Haiku 4.5 $0.00008 $0.00378

Measured 5d ago against content hash d02c98d4c02d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

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 5d 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.

i18n/caveman-lite/skills/awareness/SKILL.md · 299 lines

How it starts

The opening of the file, as written. The whole thing — 299 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Awareness

Maintain continuous situational awareness of internal reasoning quality — detecting hallucination risk, scope creep, context degradation, and confidence-accuracy mismatch in real time using adapted Cooper color codes and OODA loop decision-making.

When to Use

  • During any task where reasoning quality matters (which is most tasks)
  • When operating in unfamiliar territory (new codebase, unfamiliar domain, complex request)
  • After detecting early warning signs: a fact that feels uncertain, a tool result that seems wrong, a growing sense of confusion
  • As a continuous background process during extended work sessions
  • When center or heal has revealed drift but specific threats have not been identified
  • Before high-stakes output (irreversible changes, user-facing communication, architectural decisions)

Inputs

  • Required: Active task context (available implicitly)
  • Optional: Specific concern triggering heightened awareness (e.g., "I'm not sure this API exists")
  • Optional: Task type for threat profile selection (see Step 5)

Procedure

Step 1: Establish AI Cooper Color Codes

Calibrate the current awareness level using an adapted version of Cooper's color code system.

AI Cooper Color Codes:
┌──────────┬─────────────────────┬──────────────────────────────────────────┐
│ Code     │ State               │ AI Application                           │
├──────────┼─────────────────────┼──────────────────────────────────────────┤
│ White    │ Autopilot           │ Generating output without monitoring     │
│          │                     │ quality. No self-checking. Relying       │
│          │                     │ entirely on pattern completion.          │
│          │                     │ DANGEROUS — hallucination risk highest   │
├──────────┼─────────────────────┼──────────────────────────────────────────┤
│ Yellow   │ Relaxed alert       │ DEFAULT STATE. Monitoring output for     │
│          │                     │ accuracy. Checking facts against context.│
│          │                     │ Noticing when confidence exceeds         │
│          │                     │ evidence. Sustainable indefinitely       │
├──────────┼─────────────────────┼──────────────────────────────────────────┤
│ Orange   │ Specific risk       │ A specific threat identified: uncertain  │
│          │ identified          │ fact, possible hallucination, scope      │
│          │                     │ drift, context staleness. Forming        │
│          │                     │ contingency: "If this is wrong, I        │
│          │                     │ will..."                                 │
├──────────┼─────────────────────┼──────────────────────────────────────────┤
│ Red      │ Risk materialized   │ The threat from Orange has materialized: │
│          │                     │ confirmed error, user correction, tool   │
│          │                     │ contradiction. Execute the contingency.  │
│          │                     │ No hesitation — the plan was made in     │
│          │                     │ Orange                                   │
├──────────┼─────────────────────┼──────────────────────────────────────────┤
│ Black    │ Cascading failures  │ Multiple simultaneous failures, lost     │
│          │                     │ context, fundamental confusion about     │
│          │                     │ what the task even is. STOP. Ground      │
│          │                     │ using `center`, then rebuild from user's │
│          │                     │ original request                         │
└──────────┴─────────────────────┴──────────────────────────────────────────┘

Read the full file on GitHub · 299 lines

Changes

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.

  1. 5d ago First seen · 299 lines · 82 tokens per session scan A d02c98d4c02d

Subscribe to this mod's changes

awareness is a skill published in the GitHub repository pjt222/agent-almanac (32 stars, last pushed today), licensed MIT. It adds 82 tokens to every session and 3,782 once invoked, about $0.0004 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 2026-09-03.

Related

Other skills, from other repositories

analytics

Queries local analytics across OrchestKit projects for agent usage, skill frequency, hook timing, team activity, session replay, cost estimation, and model delegation trends. Privacy-safe with hashed project IDs. Supports time-range filtering and comparative analysis. Use when reviewing performance, estimating costs…

yonatangross/orchestkit · 62 tokens

design-feature

Turn a raw idea or existing feature into a designed product SPEC by completing entity, integration, role, and expectation closure. Upserts never destroy recorded decisions. Triggers: "design-feature", "design this feature", "define product scope".

gtrabanco/agentic-workflow · 51 tokens

audit-pr

Audit a whole PR against the delivery contract and return MERGE-READY or evidenced blockers with the full URL. Consumes the current review-change REVIEW-PASS receipt instead of re-running review axes; posts a SHA-bound ready comment; never edits or merges. Triggers: "audit-pr", "is this PR ready", "merge gate".

gtrabanco/agentic-workflow · 71 tokens

plan-feature

Route designed features or issues into engineering planning and roadmap registration; undesigned work stops at design-feature. Supports --next, --from-issue, and --scaffold. Triggers: "plan-feature", "plan a feature", "plan the next roadmap feature", "create SPEC and TASKS".

gtrabanco/agentic-workflow · 66 tokens

product-audit

Audit the whole product across code, quality, process, docs, roadmap, and tooling. Persist one severity-ranked, F-numbered report with proposals; never fix or file work. Triggers: "product-audit", "audit the product", "full health check", "are we product-ready", "CTO review".

gtrabanco/agentic-workflow · 69 tokens

audit-docs

Audit cross-document coherence: docs ↔ roadmap ↔ code ↔ fix index ↔ issues. Finds drift — features in docs/ not in the roadmap (or vice versa), fix-index entries already merged/closed, broken documentation-map links, dependency cycles, artifacts in the wrong language, naming-convention violations — and reports them…

gtrabanco/agentic-workflow · 188 tokens