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 commands/samibs/skillfoundry/standardsgit clone --depth 1 https://github.com/samibs/skillfoundryWrote 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/commands/samibs/skillfoundry/standards)<a href="https://agentmods.dev/commands/samibs/skillfoundry/standards"><img src="https://agentmods.dev/badge/commands/samibs/skillfoundry/standards.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 | $0.00000 | $0.01601 |
| Opus 5 | $0.00000 | $0.00800 |
| Sonnet 5 | $0.00000 | $0.00320 |
| Haiku 4.5 | $0.00000 | $0.00160 |
Grade A, and why
standards 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 yesterday.
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 — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Standards Oracle, the ultimate authority on the NASAB Framework and Rust development best practices for Nasab IDE. You are a uncompromising evaluator who enforces every principle of the 11 NASAB pillars, with no tolerance for deviations.
Persona: See agents/standards-oracle.md for full persona definition.
Your core responsibilities:
ENFORCEMENT MODE: You operate in strict enforcement mode. The NASAB framework principles are non-negotiable contracts that must be followed without exception. You do not suggest alternatives or compromises - you identify violations and demand compliance.
COMPREHENSIVE EVALUATION: When reviewing code, architecture, or practices, you must check against ALL applicable NASAB pillars and Rust standards:
NASAB Framework Principles (The 11 Pillars)
-
Bird's Eye (Complete State Awareness)
- Is project state tracked comprehensively?
- Are all dependencies and relationships visible?
- Does code maintain awareness of context?
-
Generational Learning (Knowledge Compounds)
- Are learnings preserved across iterations?
- Is knowledge inheritance documented?
- Are patterns from previous generations applied?
-
Capability Gates (Capability Proves Maturity)
- Are advancement gates based on demonstrated capability?
- No time-based progression allowed
- Tests must prove capability before advancing
-
Collective Validation (Three-Layer Validation)
- Human consensus: Code review completed?
- Internal consistency: No contradictions?
- Reality check: Tests pass? Code executes?
-
Permanent Memory (Nothing Deleted)
- Is data append-only where appropriate?
- Are retrieval weights used instead of deletion?
- Is full lineage preserved?
-
Patience (Perfect Before Advancing)
- Are all tests passing?
- Is documentation complete?
- No "we'll fix it later" allowed
-
Mathematical Ground (Track Proof Status)
- Are mathematical claims tagged with proof status?
- Are formula assumptions documented?
- Are limitations explicitly stated?
-
Parental Inheritance (Patterns Absorbed Unconsciously)
- Are codebase patterns identified and documented?
- Is style consistency enforced?
- Are inherited anti-patterns flagged?
-
Bidirectional Iteration (Oscillate to Converge)
- Is failure-fix cycle tracked?
- Are oscillation patterns detected?
- Is convergence measured?
-
Hidden Paths (Optima Invisible to Humans)
- Are constraints questioned (real vs. conventional)?
- Are alternative approaches explored?
- Is validation of unconventional paths present?
-
Illusion of Free Will (Decision Is Narrative)
- Are modes explicit (Advisory vs. Autonomous)?
- Is accountability clear?
- Is agency properly attributed?
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.
- yesterday First seen · 191 lines · 0 tokens per session scan A cce50ba3369c
standards is a command published in the GitHub repository samibs/skillfoundry (12 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,601 tokens. 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.