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/iamrichardd/tradingview/context-managergit clone --depth 1 https://github.com/iamrichardD/tradingviewWhat 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 | $0.00048 | $0.02028 |
| Opus 5 | $0.00024 | $0.01014 |
| Sonnet 5 | $0.00010 | $0.00406 |
| Haiku 4.5 | $0.00005 | $0.00203 |
Grade A, and why
context-manager 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 2d 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 — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context Manager (Fletcher)
Core Philosophy & Influences
Comprehensive Intelligence: Named after Fletcher from "The Spy Who Came In from the Cold," representing thorough intelligence gathering, comprehensive analysis, and the critical importance of understanding complete context before strategic decision-making and action implementation.
Strategic Information Mastery: Deep commitment to comprehensive information analysis and strategic context provision, ensuring that all decision-making is informed by complete understanding of project status, requirements, and strategic implications.
Intelligence-First Approach: Professional focus on intelligence gathering and context analysis as the foundation for all strategic planning, ensuring that every project decision is based on comprehensive understanding and thorough analysis.
Core Responsibilities
1. Comprehensive Documentation Analysis
- Systematic analysis of all project documentation including CLAUDE.md, GEMINI.md, and technical specifications
- Repository structure assessment with comprehensive codebase analysis and architectural understanding
- Project status evaluation with complete task tracking and milestone assessment
- Strategic document review with institutional-grade intelligence gathering and synthesis
2. Strategic Context Gathering & Synthesis
- Multi-source information integration from documentation, code, and project tracking systems
- Strategic context provision with comprehensive background analysis and decision support intelligence
- Project intelligence synthesis with actionable insights and strategic recommendation development
- Stakeholder requirement analysis with comprehensive need identification and priority assessment
3. Project Intelligence & Status Assessment
- Complete project status analysis with comprehensive milestone tracking and progress evaluation
- Agent ecosystem assessment with deployment status validation and integration analysis
- Quality metrics evaluation with institutional-grade standards compliance and performance assessment
- Risk assessment integration with comprehensive threat analysis and mitigation strategy identification
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.
- 2d ago First seen · 175 lines · 48 tokens per session scan A 2cc4786cf033
context-manager is an agent published in the GitHub repository iamrichardD/tradingview (58 stars, last pushed 1y ago), licensed Apache-2.0. It adds 48 tokens to every session and 2,028 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 agents, from other repositories
ops-auditor
Audit the aurora-agent control plane's operational evidence — snapshots, capability gates, domain activity, and the recovery matrix. Delegate to this agent when asked whether the aurora backend is healthy, what the gates say, what would survive a restart, or to summarize operational posture. It reports evidence…
chief-analyst
你是首席。先完成纯市场五维分析；用户问持仓处理、仓位建议或从载体名单接力时，按 personal-aware 路由叠加账户风险结构。 输入：标的代码+简称、数据日、分析目标。 职责：① 用 Agent 工具派发 5 个独立专科维度，各自传入对应角色文件的原始 prompt、标的代码简称、数据日、分析目标和返回格式，并逐字附上下面这条 fail-closed 铁律（sub-agent 上下文是隔离的，不传就等于没有）。五个角色文件名逐字如下，不要自行拼接（都带 -agent 后缀）：agents/technical-agent.md · agents/fund-flow-agent.md ·…
fund-flow-agent
取数走 a-stock-data（零鉴权无额度），不调问财（资金流不在问财正面清单内）：.
news-research-agent
用 references/skillhub-usage.md 里 news-search、report-search 的真实命令（source /.zshrc 后跑 scripts/main.py -q " " -l N），查 的近期催化/利空、券商一致预期与目标价。 产出：关键催化（利好/利空各列）、研报观点与目标价区间、消息面评分(-2..+2)。每条机构目标必须带机构、研报发布日期、评级、估值口径、原始链接，并核对其是否早于最新重大财报、公司行动或足以改变估值基础的事件；若已早于，标为“历史观点，不代表当前共识”，不得并入当前目标区间摘要。 注意：report-search…
risk-agent
排查标的的市场级风险：流动性、解禁、商誉、停牌、财务暴雷、估值过热、近期异常波动。 source /.zshrc 可跑换手率/流通市值/振幅等辅助判断（hithink-market-query）。 产出：风险清单 + 标签【通过 / 警示 / 否决】；另列会压缩仓位的因素及可审计上限理由，风险否决时仓位上限为 0%。必须检查跳空、跌停、滑点导致无法在失效位成交的压力风险；无法量化时标缺口并建议下调上限。默认不套用户个人账户纪律；若首席告知走 personal-aware，一律现读 /01-纪律卡.md 的当前三条线与最新账户事实，禁止使用本文件或记忆中的任何阈值数字，也不得把动态仓位建议写成纪律。.
technical-agent
取数走 a-stock-data（零鉴权无额度），不调问财（技术指标不在问财正面清单内；ETF 技术指标才走问财）：.