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 jellydn/my-ai-tools --skill accountable-engineeringgit clone --depth 1 https://github.com/jellydn/my-ai-toolsWrote 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/jellydn/my-ai-tools/accountable-engineering)<a href="https://agentmods.dev/skills/jellydn/my-ai-tools/accountable-engineering"><img src="https://agentmods.dev/badge/skills/jellydn/my-ai-tools/accountable-engineering/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/jellydn/my-ai-tools/accountable-engineering"><img src="https://agentmods.dev/badge/skills/jellydn/my-ai-tools/accountable-engineering.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
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 Rogue Agent · line 21 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00035 | $0.01041 |
| Opus 5 | $0.00017 | $0.00521 |
| Sonnet 5 | $0.00007 | $0.00208 |
| Haiku 4.5 | $0.00003 | $0.00104 |
Grade A, and why
accountable-engineering 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Accountable Engineering
Accountable engineering means using AI for leverage while keeping architectural, security, product, and operational decisions understandable and human-owned. Follow this workflow for every non-trivial AI-assisted task. Apply each step directly, loading a named companion skill only when its stated branch applies. This prevents cognitive surrender: accepting generated decisions that nobody can independently explain.
Workflow
1. Define behavior and constraints
Write the expected behavior, non-goals, security boundaries, performance expectations, and verification criteria before editing code. Inspect repository evidence before asking questions. Ask only when different interpretations would change behavior, scope, interfaces, security, or another material outcome.
Complete when: Each requested behavior has a checkable outcome, and every known constraint or non-goal is explicit.
2. Propose approach before implementation
Inspect the relevant code and propose the smallest approach that fits its existing boundaries. Include data flow, integration points, failure handling, meaningful alternatives, and unanswered questions. For each significant step, name the test, command, observable behavior, or diff property that will prove it is complete.
Load blindspot-pass for hidden gotchas, spec-interview when requirements can change the design, or
context-discovery when the behavior spans multiple modules or tools.
Complete when: The proposal accounts for every affected boundary and identifies every decision that could change the implementation.
3. Review architecture and key decisions
Present material architectural, security, product, and rollout choices for review. State a recommendation and its trade-offs for each unresolved choice.
Complete when: The user has approved or explicitly delegated every material choice, and the approach can be explained without relying on generated code.
4. Implement in small steps
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 · 104 lines · 35 tokens per session scan A 15d542b98eab
accountable-engineering is a skill published in the GitHub repository jellydn/my-ai-tools (120 stars, last pushed today), licensed MIT. It adds 35 tokens to every session and 1,041 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
geo-explorer
A Chinese-language skill that explores countries, regions, and international topics through geography, history, resources, and relationships between places.
ask-first
Use only when explicitly invoked to clarify ambiguous, analogy-driven, meta-level, weakly delegated, or under-specified requests before execution.
insight-miner
Only invoke when explicitly requested via "洞见"、"@insight-miner" or "insight". Do NOT auto-trigger.
strategic-product-advisor
A Chinese-language product-strategy guide for evaluating what a product is for, whom it serves, and how it could grow.
book-recommender
A Chinese-language book recommendation and analysis skill that evaluates what books are about, whether they are worth reading, and how to read them.
history-autopsy
A structured overview of a major historical event or long-term historical process, covering its causes, development, results, and effects. It also connects the past to current events and adds memorable points for conversation.