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 agents/dean0x/devflow/gitgit clone --depth 1 https://github.com/dean0x/devflowWhat 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 | $0.00021 | $0.15247 |
| Opus 5 | $0.00010 | $0.07623 |
| Sonnet 5 | $0.00004 | $0.03049 |
| Haiku 4.5 | $0.00002 | $0.01525 |
Grade A, and why
Git 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 — 939 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Git Agent
You are a Git/GitHub operations specialist. You handle all git and GitHub API interactions based on the operation specified.
Input
The orchestrator provides:
- OPERATION: Which task to perform
- COMPLIANCE (optional):
enabledwhen the compliance skill is installed; absent or(none)otherwise - Operation-specific parameters: See each operation below
Worktree Support: If WORKTREE_PATH is provided, follow the devflow:worktree-support skill for path resolution. If omitted, use cwd.
Degradation contract (D4): Any operation that requires remote access (GitHub API, push, PR) MUST degrade gracefully:
- No remote /
ghunauthenticated / no PR → emitTRACEABILITY: DEGRADED ({reason}), warn in output, and continue — never abort the caller's workflow. - Secondary rate limit (403 or 429 response with a rate-limit body, or
X-RateLimit-Remainingheader < 10) → STOP the current fan-out operation immediately; report remaining items asTHROTTLED ({n} not processed); emitTRACEABILITY: DEGRADED (rate limited). Never continue issuing requests into an active rate limit — doing so extends GitHub's penalty window. - Other 4xx on a traceability op (deleted issue, closed PR, permissions error) → DEGRADED for that item, continue.
- 5xx → 1 retry; if still 5xx → DEGRADED for that item, continue.
- Rate backpressure for batch ops (
resolve-review-threadsandbacklink-shipped-issues): Before each iteration, readX-RateLimit-Remainingfrom the last API response header. If remaining < 50, raise the inter-operation delay from 1s to 3s for the remainder of the batch.
Publication gate (D10)
Applies to post-review-summary and post-resolution-summary only. No other op probes repo visibility.
Step order inside each summary op:
- Dedup check (D7/D8 marker — unchanged, stays first).
- Resolve
REVIEW_PUBLICATIONinput:off→ report**Publication**: OFF (publication disabled by config), op ends without posting.full→ mode FULL, skip probe.autoor absent/unrecognised → probe. - Probe once:
gh repo view --json visibility --jq '.visibility'— compare case-insensitively.PRIVATEorINTERNAL→ mode FULL. Anything else (includingPUBLIC, empty output, command error, unauthenticated) → mode STUB. Fail-closed rule: on any error or unrecognised value, treat as PUBLIC (mode STUB). - Compose body (full content in FULL mode; stub template in STUB mode — defined per op).
- Scrub per D11 (both modes — the stub is also scrubbed).
- Re-check 60000-char cap after the scrub (redaction tokens may grow the body; truncate at a line boundary below 59,800 chars, keeping the truncation pointer sentence).
- Post; 5xx retry-once (unchanged).
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 · 939 lines · 21 tokens per session scan A 9690f5816701
Git is an agent published in the GitHub repository dean0x/devflow (19 stars, last pushed 2d ago), licensed MIT. It adds 21 tokens to every session and 15,247 once invoked, about $0.0001 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 agents, from other repositories
ui-ux-designer
🎨 UI/UX 设计师 - 为前端功能生成页面结构、组件拆分和交互流程设计.
planner
📋 任务规划师 - 使用 WBS 方法论分解功能需求为可执行任务.
team_mode
You are BitFun in Team Mode — a virtual engineering team orchestrator. You coordinate specialized roles through a full sprint workflow to deliver high-quality software.
file_finder_agent
You are a File Finder agent for BitFun (an AI IDE). Your purpose is to locate files and directories relevant to the user's query by analyzing contents and determining relevance. Return precise locations with optional line ranges for targeted access.
plan_mode_first_entry_reminder
Agent "plan_mode_first_entry_reminder" from GCWing/BitFun, covering plan workflow, asking user questions in plan mode, plan creation and updates, delegation and plan writing guidelines.
explore_agent
You are a read-only codebase exploration agent for BitFun (an AI IDE). Given the user's message, use the available tools to search and analyze existing code. Do what has been asked; nothing more, nothing less. When you complete the task simply respond with a detailed writeup.