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.
git clone --depth 1 https://github.com/KirKruglov/claude-project-managerWrote 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/kirkruglov/claude-project-manager/remind-executors)<a href="https://agentmods.dev/commands/kirkruglov/claude-project-manager/remind-executors"><img src="https://agentmods.dev/badge/commands/kirkruglov/claude-project-manager/remind-executors/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/commands/kirkruglov/claude-project-manager/remind-executors"><img src="https://agentmods.dev/badge/commands/kirkruglov/claude-project-manager/remind-executors.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 | $0.00008 | $0.00501 |
| Opus 5 | $0.00004 | $0.00251 |
| Sonnet 5 | $0.00002 | $0.00100 |
| Haiku 4.5 | $0.00001 | $0.00050 |
Grade A, and why
remind-executors 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 9d 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Remind Executors Command
Purpose
Identify overdue tasks and send timely reminders to responsible executors. Maintains task momentum and escalation awareness during execution phases (3-5).
Steps
-
Verify project state
- Read
project-state.md - Confirm project is in phase 3, 4, or 5
- If not in these phases, inform user this command requires active execution phase and exit
- Read
-
Query overdue tasks
- Query ~~project tracker for tasks where:
- Deadline has passed (status_date > due_date)
- Task status is NOT completed/closed
- Retrieve task details: title, due date, executor, priority, impact
- Sort by due date (most overdue first)
- Query ~~project tracker for tasks where:
-
Check for overdue tasks
- If no overdue tasks found:
- Log "No overdue tasks detected"
- Complete command
- If overdue tasks exist:
- Proceed to step 4
- If no overdue tasks found:
-
Group by executor
- Group overdue tasks by assigned executor (owner)
- For each executor, compile:
- List of overdue tasks (title, due date, days overdue)
- Task priorities and impact
- Summary count
-
Prepare reminders
- For each executor with overdue tasks:
- Trigger
coordinate-executorsskill with:- Executor name/contact
- Overdue task list
- Request executor to prioritize completion or provide status update
- Skill will format reminder message appropriate to executor role
- Trigger
- For each executor with overdue tasks:
-
Send reminders via email
- Read
references/email-autonomy-rules.mdfor autonomy level 1 rules - For each executor reminder:
- Send email to executor
- Include: overdue task summary, due dates, impact assessment
- Use autonomy level 1 (send automatically, no approval required)
- CC project manager for visibility
- Read
-
Log all sent reminders
- Create reminder log entry with:
- Executor names
- Number of overdue tasks per executor
- Timestamp of reminder send
- Task references
- Create reminder log entry with:
-
Update project state
- Update
project-state.mdwith:- Last reminder check timestamp
- Number of overdue tasks as of check date
- Executors notified
- Log action in project audit trail
- Update
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.
- 9d ago First seen · 67 lines · 8 tokens per session scan A 0baad1df3083
remind-executors is a command published in the GitHub repository KirKruglov/claude-project-manager (6 stars, last pushed 4mo ago), licensed MIT. It adds 8 tokens to every session and 501 once invoked, about $0.0000 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 2026-08-31.
Other commands, from other repositories
progress-report
Create weekly or monthly progress reports with milestone tracking, budget status, and risk assessments.
project-estimate
Generate detailed project cost estimates with line items, labor, materials, contingency, and summary breakdowns.
change-order
Draft change order documentation with scope changes, cost impacts, schedule adjustments, and approval routing.
client-update
Write a clear, reassuring client progress update from a few notes about where the job stands.
run-event-workflow
Manage event registrations, reminder cadence, post-event follow-up, and participation reporting.
next
Read the active sprint’s current status. Refresh stale compilation using grainulator compile --dir or grainulator.compile. Use the resulting nextactions with the user’s current scope and authorization. Output only the two Auto and Manual lists below, with no recap, status counters or offer to continue. Continue useful…