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 agentmods add skills/deevsdeevs/agent-system/97-devnpx skills add DeevsDeevs/agent-system --skill 97-devgit clone --depth 1 https://github.com/DeevsDeevs/agent-systemWhat 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 | $0.00046 | $0.00787 |
| Opus 5 | $0.00023 | $0.00394 |
| Sonnet 5 | $0.00009 | $0.00157 |
| Haiku 4.5 | $0.00005 | $0.00079 |
Grade A, and why
97-dev 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 2d 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
97-dev: Programmer's Wisdom
Distilled principles from 97 Things Every Programmer Should Know. Apply when writing, reviewing, or making design decisions.
Core Philosophy
Code is design. Software development is a creative discipline requiring craftsmanship, not mechanical construction.
The code tells the truth. Documentation lies, comments decay - only executable code reveals actual behavior. Make code self-explanatory.
Care about your code. Excellence stems from attitude, not just knowledge. Craft elegant code that is clearly correct.
Quick Principles
| Principle | One-liner |
|---|---|
| Simplicity | Remove everything unnecessary; less is more |
| Boy Scout | Leave code cleaner than you found it |
| DRY | Single authoritative representation for each piece of knowledge |
| SRP | One reason to change per class/module/function |
| Comments | Comment only what code cannot say - explain why, not what |
| Tech debt | Pay immediately or track the compounding interest |
| Testing | Non-negotiable professional obligation |
| Errors | Always check, always handle, every time |
| Next commit | Know exactly what you're committing before you start |
| Users | You are not the user - observe, don't assume |
Detailed References
Load these when you need deeper guidance on specific topics:
references/simplicity.md
When: Refactoring bloated code, making architectural decisions, deciding what to remove, questioning if features are needed. Covers: Beauty in simplicity, reduction over addition, improving by removing, code as design.
references/quality.md
When: Code review, enforcing standards, improving maintainability, designing APIs and interfaces. Covers: Boy Scout Rule, DRY principle, Single Responsibility, interface design, code as truth.
references/professionalism.md
When: Career decisions, team dynamics, handling pressure, technical debt discussions, attitude check. Covers: Professional responsibility, caring about code, long-term thinking, prudent debt management.
What ships with it
7 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.
- 2d ago First seen · 78 lines · 46 tokens per session scan A 25e7f5045d76
97-dev is a skill published in the GitHub repository DeevsDeevs/agent-system (40 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 46 tokens to every session and 787 once invoked, about $0.0002 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
scientific-critical-thinking
Evaluate scientific claims and evidence quality. Use for assessing experimental design validity, identifying biases and confounders, applying evidence grading frameworks (GRADE, Cochrane Risk of Bias), or teaching critical analysis. Best for understanding evidence quality, identifying flaws. For formal peer review…
lessons-learned
Mandatory pre-flight-search reference. Contains the Seats.aero workflow (pull ALL programs first), source accuracy hierarchy, Southwest/Companion Pass specifics, small-market caveats, and Duffel limitations.
hello-world
A simple example skill demonstrating the OCX skill format.
memory-manager
Standardized workflow for discovering, reading, writing, and compacting the project's memory file (memory.instructions.md) to persist context across AI chat sessions, with a permanent Knowledge Base for cross-session decisions and lessons learned.
tdd-generate-docs
Workflow for auditing, designing, and writing structured user & developer documentation based on the Diátaxis Framework (Tutorials, How-to, Reference, Explanation) using test-derived living examples.
guided-learning
AI-Guided Learning mentor. Guides the user step-by-step to build and learn a new technology without writing the final code for them.