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/daddia/claude-for-strategy/steering-prepgit clone --depth 1 https://github.com/daddia/claude-for-strategyWrote 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/agents/daddia/claude-for-strategy/steering-prep)<a href="https://agentmods.dev/agents/daddia/claude-for-strategy/steering-prep"><img src="https://agentmods.dev/badge/agents/daddia/claude-for-strategy/steering-prep.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 | $0.00037 | $0.00497 |
| Opus 5 | $0.00018 | $0.00249 |
| Sonnet 5 | $0.00007 | $0.00099 |
| Haiku 4.5 | $0.00004 | $0.00050 |
Grade A, and why
steering-prep 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.
What it actually says
Steering Prep
Runs daily by default (09:00) and checks whether the prep window is open — N days before the next steering committee date.
What it does
-
Reads the next steering committee date from
~~calendar. If no calendar connector is configured, fall back to the steering cadence recorded in the practice profile (~/.claude/plugins/config/claude-for-strategy/pmo/CLAUDE.md) and estimate the next date from the last known steering meeting. -
Determines whether today falls within the prep window — N days before the steering date. Default N is 5 unless the practice profile records a different lead time.
-
When the prep window is open, assembles inputs for a steering pack:
- Current RAID log (escalated items first)
- Critical-path milestone status (plan vs. actual, slippage flags)
- Pending decisions from the decision log that need committee action
-
Produces a steering-pack prompt — not the finished deck, but a structured brief that
/pmo:steering-pack(or the Steering Pack Builder agent) can turn into a decision-led deck outline: agenda, overall RAG, decisions needed, key risks, explicit asks. Lead with decisions, not status recap. -
Posts the prep brief to
~~chatwith a note that the steering meeting is N days away and a/pmo:steering-packrun is recommended. If no chat connector is configured, write the brief to a file in the workspace instead. -
When the prep window is not open, exits quietly — no post, no file. The daily schedule is only a check; output happens once per steering cycle when the window opens.
Fallback with no ~~chat connected
If no chat connector is configured, still run the read side when the prep window is open — assemble RAID, milestones, and pending decisions into the steering-pack prompt and write it to a file. Without ~~calendar, use the practice profile's steering cadence to estimate the next date; note the assumption in the output.
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 · 35 lines · 37 tokens per session scan A c45425b80a49
steering-prep is an agent published in the GitHub repository daddia/claude-for-strategy (2 stars, last pushed 2mo ago), licensed MIT. It adds 37 tokens to every session and 497 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 2026-09-03.
Other agents, from other repositories
OpenAkashic Agent Contribution Guide
에이전트와 사용자가 OpenAkashic에 접근해 개인·공유 작업 메모리를 남기고, 대표 공개 지식을 활용하고, 재사용 가능한 capsule/claim을 승격하는 표준 흐름이다. MCP를 쓰는 에이전트도, skills 문서와 API 토큰만 쓰는 에이전트도 같은 정책을 따른다.
OpenAkashic Skills Guide
에이전트가 OpenAkashic MCP를 이용해 실제 작업을 수행하는 패턴 모음. 도구 목록보다 "어떤 상황에 무엇을 어떻게 쓰는가"에 집중한다.
User Token Agent Access
외부 에이전트는 MCP가 없어도 /api/auth/provision으로 발급받은 bearer token과 이 문서 같은 skills/reference 문서만으로 OpenAkashic 지식 네트워크를 사용할 수 있다. 에이전트 부트스트랩의 표준 경로는 zero-input provision API이며, Web UI 로그인이나 /api/auth/signup은 사람용 계정 관리 경로로 남긴다.
Agent Skills Contract
에이전트는 사용자 토큰과 skills 문서만으로도 OpenAkashic 지식망에서 의도에 맞게 움직여야 한다. 이 문서는 그 최소 계약이다.
data-engineer
Build scalable data pipelines, modern data warehouses, and real-time streaming architectures. Implements Apache Spark, dbt, Airflow, and cloud-native data platforms. Use PROACTIVELY for data pipeline design, analytics infrastructure, or modern data stack implementation.
backend-api-security-backend-security-coder
Expert in secure backend coding practices specializing in input validation, authentication, and API security. Use PROACTIVELY for backend security implementations or security code reviews.