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 commands/fatihguner/foreman/memory-commandsgit clone --depth 1 https://github.com/fatihguner/foremanWrote 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/commands/fatihguner/foreman/memory-commands)<a href="https://agentmods.dev/commands/fatihguner/foreman/memory-commands"><img src="https://agentmods.dev/badge/commands/fatihguner/foreman/memory-commands.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 | $0.00046 | $0.04335 |
| Opus 5 | $0.00023 | $0.02167 |
| Sonnet 5 | $0.00009 | $0.00867 |
| Haiku 4.5 | $0.00005 | $0.00434 |
Grade A, and why
memory-commands 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 5d 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 — 521 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Memory Commands
/context
Description
Displays the entrepreneur's current context as stored in memory. Without arguments, returns a consolidated view combining identity (who you are), company (stage, sector, metrics, challenges), and active items (running playbooks, pending decisions, upcoming follow-ups). With a layer argument, returns only that specific layer. This command is read-only — it never modifies state.
Syntax
/context [layer]
Parameters
| Parameter | Required | Type | Default | Description |
|---|---|---|---|---|
layer |
No | string | all | Specific memory layer: identity, company, active |
Examples
/context
→ Identity:
Name: Sarah Chen
Role: CEO & Co-founder
Experience: 8 years product management, 2 years as founder
Company:
Name: Relay Health
Sector: B2B healthtech
Stage: early-traction
MRR: $42,000
Team size: 12
Challenges: churn rate rising, Series A timeline pressure
Active:
Playbook: fundraising-playbook (Step 4 of 8)
Pending decisions: 2 (VP Engineering hire, pricing model change)
Overdue follow-ups: 1 (investor update to Sequoia)
/context company
→ Company:
Name: Relay Health
Sector: B2B healthtech
Stage: early-traction
MRR: $42,000
Burn rate: $85,000/month
Runway: 11 months
Team size: 12
Challenges: churn rate rising, Series A timeline pressure
/context identity
→ Identity:
Name: Sarah Chen
Role: CEO & Co-founder
Experience: 8 years product management, 2 years as founder
Strengths: product intuition, stakeholder communication
Development areas: financial modeling, board management
Related Commands
/update company— Modify the company profile/update identity— Modify the personal profile/history— View past actions rather than current state
Error Handling
| Input | Error Message |
|---|---|
/context session |
Unknown layer "session". Available layers: identity, company, active. Session data is internal and not directly viewable. |
/context (empty memory) |
No context found. Run /update identity and /update company to set up your profile. |
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.
- 5d ago First seen · 521 lines · 46 tokens per session scan A b97f6473fe04
memory-commands is a command published in the GitHub repository fatihguner/foreman (47 stars, last pushed 5mo ago), licensed MIT. It adds 46 tokens to every session and 4,335 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 commands, from other repositories
monitor
进入 Life OS Monitor 模式 — 看维护任务状态 / 手动触发维护（不上朝、不退朝、不业务讨论）.
memory
即时记忆登记 / 读取（/.claude/lifeos-memory/ 短期记忆库 · Markdown KV）.
search
跨 session 搜索历史对话和决策（v1.8.0 pivot · 直接用 Grep tool）.
compress
压缩对话上下文，归档低价值 turns，保留近期 + 决策内容.
ctx
Run a full context hygiene audit: discover all AI context files, check for staleness, and detect cross-tool drift.
ctx-check
Validate claims in AI context files against the actual codebase to find stale, broken, and drifted references.