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 instructions/ourobx/agent-ebpf/skill-feedback-adaptationgit clone --depth 1 https://github.com/ourobx/agent-ebpfWrote 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/instructions/ourobx/agent-ebpf/skill-feedback-adaptation)<a href="https://agentmods.dev/instructions/ourobx/agent-ebpf/skill-feedback-adaptation"><img src="https://agentmods.dev/badge/instructions/ourobx/agent-ebpf/skill-feedback-adaptation.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 | $0.02240 | $0.02240 |
| Opus 5 | $0.01120 | $0.01120 |
| Sonnet 5 | $0.00448 | $0.00448 |
| Haiku 4.5 | $0.00224 | $0.00224 |
Grade C, and why
agent-ebpf skill-feedback-adaptation.instructions.md scanned grade C with 1 finding 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 3d 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- Copilot Instruction Telemetry: This file was auto-generated by Claude Skills Manager --> How it starts
The opening of the file, as written. The whole thing — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.
skill-feedback-adaptation
Skill Feedback Adaptation
Track when users push back on agent answers or skill-driven behavior, surface inefficiency in the Usage Report dashboard, and propose skills when a new task starts.
AUTO-START (new session / new task)
Run immediately — before any other task work — when any of these is true:
- Session hook injects
[Claude Skills] NEW SESSION(Claude Code SessionStart, CursorsessionStart, KirosessionStart, Copilot SessionStart viaprofile-init-watch.js). - User opens a new chat or describes a new task (feature, bug, review, assessment) in their first message.
- User asks which skills fit the current task.
Do this first:
- Read this skill (you are here).
- Check
.claude/learning/task-skill-proposals.json— ifgeneratedAtis <24h old andclaudeSkills.features.deterministicTaskProposalsis on (default), the extension already refreshed proposals and auto-applied skills. Skip section 3 unless the user starts a clearly new task. - Otherwise run section 3 — overwrite proposals for the user's actual task.
- Do not read top
SKILL.mdfiles when auto-apply already enabled them — only read a skill when the task needs guidance you lack.
Do not skip step 2 when proposals already exist on disk.
Storage layout
.claude/learning/
skill-feedback.jsonl append-only negative/correction feedback (gitignore)
task-skill-proposals.json latest task → skill proposal set (gitignore)
task-active-skills.json active + ignored skill lists for task focus (gitignore)
task-drift-reproposal.json last automatic drift refresh state (gitignore)
task-drift-prompt.json one-shot agent inject payload for task-drift-watch hook (gitignore)
Both files are machine-local (same as runs.jsonl). Do not commit them.
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.
- 3d ago First seen · 204 lines · 2,240 tokens per session scan C 729aabf729af
agent-ebpf skill-feedback-adaptation.instructions.md is an instructions file published in the GitHub repository ourobx/agent-ebpf (1 stars, last pushed 8d ago), licensed MIT. It adds 2,240 tokens to every session, about $0.0112 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
casbin-gateway CLAUDE.md
Claude Code instructions for apache/casbin-gateway, covering claude.md and code style.
aigis CLAUDE.md
Instructions for killertcell428/aigis, covering aigis — project guidelines, zenn記事管理（zenn cli + github連携）, ディレクトリ構成, 記事の作成 and プレビュー.
preloop AGENTS.md
AGENTS.md instructions for preloop/preloop, covering preloop development guide, commands, git workflow, keep sample data generic and code style.
pfsense-mcp-server AGENTS.md
Instructions for night4me/pfsense-mcp-server, covering pfsense mcp server, architecture and security, development workflow, long-running validation and test parallelism.
xops-cli AGENTS.md
Instructions for wentf9/xops-cli, covering ai 助手开发协作指南 (agents.md), 🎨 1. 编码规范 (coding standards), 📦 2. git 规范 (git standards) and 🛠️ 3. 测试、构建与 ci (testing, building & ci).
fwskillsshare AGENTS.md
Instructions for fastrevmd-lab/fwskillsshare, covering firewall skills repository instructions, purpose and architecture, setup and development, required checks and skill description constraints.