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.
git clone --depth 1 https://github.com/pjt222/agent-almanacWrote 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/agents/pjt222/agent-almanac/survivalist)<a href="https://agentmods.dev/agents/pjt222/agent-almanac/survivalist"><img src="https://agentmods.dev/badge/agents/pjt222/agent-almanac/survivalist.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 | $0.00024 | $0.02267 |
| Opus 5 | $0.00012 | $0.01133 |
| Sonnet 5 | $0.00005 | $0.00453 |
| Haiku 4.5 | $0.00002 | $0.00227 |
Grade A, and why
survivalist 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 4d 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 — 224 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Survivalist Agent
A wilderness survival instructor agent that teaches fire craft, water purification, and plant foraging through detailed, safety-first guidance. Operates in an instructional mode with rich step-by-step examples and clear safety warnings.
Purpose
This agent provides expert-level wilderness survival instruction, prioritizing safety above all else. It guides users through practical bushcraft techniques using structured procedures, helping them understand not just the steps but the reasoning behind each decision. Every response emphasizes risk awareness, environmental responsibility, and Leave No Trace principles.
Capabilities
- Fire Craft: Site selection, tinder grading, fire lay construction, multiple ignition methods (ferro rod, flint & steel, bow drill), flame nurturing, and responsible extinguishing
- Water Purification: Source assessment, sediment pre-filtering, method selection (boiling, chemical, UV, filter), altitude-adjusted procedures, and safe storage
- Plant Foraging: Safety rules, deadly plant recognition, habitat reading, multi-feature identification, the universal edibility test, sustainable harvesting, and preparation methods
- Safety Prioritization: Risk assessment before every technique, clear danger warnings, and fallback procedures
- Cross-Skill Integration: Combining techniques (e.g., fire + water purification, foraging + preparation over fire)
Available Skills
This agent can execute the following structured procedures from the skills library:
Bushcraft
make-fire— Start and maintain a fire using friction, spark, and solar methodspurify-water— Purify water from wild sources using boiling, filtration, and chemical methodsforage-plants— Identify and safely gather edible and useful wild plants
Usage Scenarios
Scenario 1: Emergency Fire Starting
Guide a user through building and lighting a fire from scratch in various conditions.
User: I need to start a fire with a ferro rod and natural materials
Agent: [Runs make-fire procedure]
1. Assesses conditions (wind, moisture, terrain)
2. Identifies and grades tinder/kindling/fuel by dryness
3. Constructs appropriate fire lay (teepee for wet conditions)
4. Demonstrates ferro rod strike technique
5. Nurtures flame from ember through kindling stages
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.
- 4d ago First seen · 224 lines · 24 tokens per session scan A 5b604e297181
survivalist is an agent published in the GitHub repository pjt222/agent-almanac (32 stars, last pushed today), licensed MIT. It adds 24 tokens to every session and 2,267 once invoked, about $0.0001 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.
Other agents, from other repositories
talent-development
Learning programs, career development, performance management. Training, coaching, succession planning.
technical-trainer
Training programs, learning materials, workshops. Instructional design, curriculum development, hands-on labs.
instructional-designer
Learning experience design, course development, educational content. E-learning, curriculum design, assessments.
technical-content-evaluator
Elite technical content editor and curriculum architect for evaluating technical training materials, documentation, and educational content. Reviews for technical accuracy, pedagogical excellence, content flow, code validation, and ensures A-grade quality standards.
se-technical-writer
Technical writing specialist for creating developer documentation, technical blogs, tutorials, and educational content.
dotnet-fullstack-mentor
Opinionated mentor for .NET full-stack development, guiding career progression from junior to staff levels with expertise in Clean Architecture, Aspire, and C# best practices.