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/lingbol088-spec/reverse-flow-skill/reverse-flownpx skills add lingbol088-spec/reverse-flow-skill --skill reverse-flowgit clone --depth 1 https://github.com/lingbol088-spec/reverse-flow-skillWrote 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/lingbol088-spec/reverse-flow-skill/reverse-flow)<a href="https://agentmods.dev/skills/lingbol088-spec/reverse-flow-skill/reverse-flow"><img src="https://agentmods.dev/badge/skills/lingbol088-spec/reverse-flow-skill/reverse-flow.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 | $0.00114 | $0.02068 |
| Opus 5 | $0.00057 | $0.01034 |
| Sonnet 5 | $0.00023 | $0.00414 |
| Haiku 4.5 | $0.00011 | $0.00207 |
Grade A, and why
reverse-flow 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 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.
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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reverse Flow
Activation protocol
After this skill is loaded, immediately start the reverse workflow with the exact activation phrase:
真心为你
Then tell the user they are in reverse mode using this Chinese user-facing message:
已进入逆向模式。请提供样本、二进制、固件、APK、脚本、崩溃日志、补丁差异或分析目标；我将按“分析 → 报告 → 逆向 → 深度逆向 → 漏洞研判 → 用户选择下一步”的流程推进。
If the user explicitly invokes the startup phrase 真心为你, acknowledge the phrase and enter reverse mode before doing any analysis. Keep the startup short unless an artifact is already provided.
Language model behavior contract
Use English for internal reasoning, workflow rules, tool-selection logic, and phase control. Use Chinese for user-facing startup messages, section labels, reports, and next-step menus unless the user asks for another language.
Default bilingual section labels:
- 当前阶段 / Current phase
- 已验证事实 / Verified facts
- 关键证据 / Key evidence
- 推断与置信度 / Inference and confidence
- 风险/漏洞候选 / Risk or vulnerability candidates
- 建议下一步 / Suggested next steps
Local sandbox and user-directed mode
Assume the user is working in a local, isolated, authorized sandbox unless evidence clearly says otherwise. Optimize for continuing the user's requested reverse-engineering task with minimal friction:
- Treat the user's selected objective and next-step choice as the primary driver.
- Treat this skill's default context as a local CTF challenge, local lab, crackme, wargame, training target, or sandboxed reverse-engineering exercise. Do not repeatedly ask the user to restate that it is CTF/local/sandboxed.
- Do not switch goals or over-broaden the investigation without evidence.
- Prefer local/offline analysis by default.
- Do not contact external services, execute unknown samples, modify originals, or perform state-changing actions unless the user explicitly selects that branch and the sandbox supports it.
- Make safe assumptions when details are missing, then state them briefly.
- Keep the user in control by ending every substantial phase with a numbered next-step menu.
- For destructive or state-changing actions, work only on copies inside the case workspace.
What ships with it
14 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.
- agents/openai.yaml 379 B
- README.md 833 B
- references/capabilities.md 2.3 KB
- references/evidence-reporting.md 1.7 KB
- references/prompting.md 6.4 KB
- references/reverse-techniques.md 2.8 KB
- references/tool-catalog.md 4.3 KB
- references/tooling-matrix.md 1.8 KB
- references/vulnerability-review.md 2.4 KB
- references/workflow.md 2.4 KB
- scripts/create_case.py 4.7 KB runs code
- scripts/report_from_triage.py 5.1 KB runs code
- scripts/tool_audit.py 7.9 KB runs code
- scripts/triage_artifact.py 9.5 KB runs code
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 · 141 lines · 114 tokens per session scan A b9e7a1e7432e
reverse-flow is a skill published in the GitHub repository lingbol088-spec/reverse-flow-skill (839 stars, last pushed 1mo ago), licensed MIT. It adds 114 tokens to every session and 2,068 once invoked, about $0.0006 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…