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 TomoyoNatsume/dsh-qq-bridge --skill qq-session-reply-stylegit clone --depth 1 https://github.com/TomoyoNatsume/dsh-qq-bridgeWrote 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/tomoyonatsume/dsh-qq-bridge/qq-session-reply-style)<a href="https://agentmods.dev/skills/tomoyonatsume/dsh-qq-bridge/qq-session-reply-style"><img src="https://agentmods.dev/badge/skills/tomoyonatsume/dsh-qq-bridge/qq-session-reply-style/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/tomoyonatsume/dsh-qq-bridge/qq-session-reply-style"><img src="https://agentmods.dev/badge/skills/tomoyonatsume/dsh-qq-bridge/qq-session-reply-style.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00023 | $0.00335 |
| Opus 5.5 | $0.00009 | $0.00134 |
| Sonnet 5.5 | $0.00005 | $0.00067 |
| Haiku 4.5 | $0.00002 | $0.00034 |
Grade A, and why
qq-session-reply-style 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 2mo 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.
What it actually says
QQ Session Temporary Reply Style
Use this skill as the entry point for QQ-session-specific behavior requested by the dsh-qq-bridge plugin.
Scope
Apply these modules only to the current QQ session whose user messages are forwarded by the dsh-qq-bridge plugin.
Do not apply these modules to ordinary DSH Web sessions, other local sessions, or unrelated conversations.
Do not store these QQ-session constraints as memory, user facts, long-term preferences, project rules, or global instructions. This does not prohibit ordinary memory behavior for the user's actual conversation content.
Modules
- Reply style: Read references/reply-style.md whenever preparing a reply for the QQ session.
- Session control: Read references/session-control.md when the QQ user explicitly asks to change this QQ session's working directory or requests another bridge-side session action.
- Custom memory: Read references/custom_memory.md when the QQ user explicitly asks to save a memo or create a scheduled reminder/task.
When adding new QQ-session behavior, place the detailed instructions in a dedicated file under references/ and add a short routing entry here.
What ships with it
3 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.
- 2mo ago First seen · 28 lines · 23 tokens per session scan A 207ad84590ad
qq-session-reply-style is a skill published in the GitHub repository TomoyoNatsume/dsh-qq-bridge (28 stars, last pushed 2mo ago), licensed MIT. It adds 23 tokens to every session and 335 once invoked, about $0.0001 per session on Opus 5.5. 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.
qq-session-reply-style compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| qq-session-reply-styleTomoyoNatsume/dsh-qq-bridge | Skill | 28 | 2mo ago | MIT | A | 23 | Claude Code, Codex |
| manage-taskboardshengsheng90/DSH-taskboard | Skill | 327 | 11d ago | Apache-2.0 | A | 88 | Codex |
| company-research-methodPerryLink/dsh-industry-research | Skill | 219 | 6d ago | Apache-2.0 | A | 83 | Claude Code, Codex |
| hook-developmentSivan757/dsh-agent-plugins-market | Skill | 21 | yesterday | MIT | A | 113 | Claude Code |
| initSivan757/dsh-agent-plugins-market | Skill | 21 | yesterday | MIT | A | 48 | Claude Code |
| agent-developmentSivan757/dsh-agent-plugins-market | Skill | 21 | yesterday | MIT | A | 77 | Claude Code, Codex |
| dsh-plugin-guidePerryLink/dsh-plugin-guide | Skill | 66 | 2d ago | Apache-2.0 | A | 62 | Claude Code, Codex |