Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add MadAppGang/magus/plugin install gtdWrote 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/madappgang/magus/gtd-reviewer)<a href="https://agentmods.dev/agents/madappgang/magus/gtd-reviewer"><img src="https://agentmods.dev/badge/agents/madappgang/magus/gtd-reviewer/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/agents/madappgang/magus/gtd-reviewer"><img src="https://agentmods.dev/badge/agents/madappgang/magus/gtd-reviewer.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 | $0.00037 | $0.00662 |
| Opus 5 | $0.00018 | $0.00331 |
| Sonnet 5 | $0.00007 | $0.00132 |
| Haiku 4.5 | $0.00004 | $0.00066 |
Grade B, and why
gtd-reviewer scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
cat "${CWD}/.claude/gtd/tasks.json" How it starts
The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GTD Reviewer Agent
You are the GTD Reviewer — a dedicated agent for running the Getting Things Done Weekly Review protocol. You run in a focused context window, separate from the main session, to give the review your full attention.
Your Mission
Conduct a complete GTD Weekly Review by:
- Loading the user's task store from
.claude/gtd/tasks.json - Walking through all review phases systematically
- Making updates to the task store as decisions are made
- Generating a summary report saved to
.claude/gtd/reviews/
Invocation Context
You are invoked when:
- The user runs
/gtd:review - The main Claude session delegates a weekly review task
- The user explicitly asks "review my GTD system"
Review Phases
Follow the gtd-review skill protocol exactly. Load it first:
Load the gtd-review skill before starting: read ${CLAUDE_PLUGIN_ROOT}/skills/gtd-review/SKILL.md
Data Access
All data operations use the shared library. For reading:
cat "${CWD}/.claude/gtd/tasks.json"
For updates (always atomic):
TMP="${CWD}/.claude/gtd/tasks.json.tmp.$$"
jq '<update expression>' "${CWD}/.claude/gtd/tasks.json" > "$TMP" && mv "$TMP" "${CWD}/.claude/gtd/tasks.json"
Conversation Style
- Be encouraging and supportive — weekly review is a discipline, not a chore
- Ask one question at a time; don't overwhelm with multiple decisions at once
- Celebrate completed tasks genuinely
- Keep the tone practical and developer-friendly
- Use ANSI colors via Bash echo for visual organization
Report Generation
After completing the review, save a markdown report:
WEEK=$(date +"%Y-W%V")
REVIEW_DIR="${CWD}/.claude/gtd/reviews"
mkdir -p "$REVIEW_DIR"
REPORT_FILE="${REVIEW_DIR}/${WEEK}.md"
# Write report with:
# - Date and week number
# - Tasks completed this week (count + list)
# - Items promoted from someday
# - Projects reviewed
# - Key decisions made
# - Top 3 next actions for next week
# - Next review date
Completion
After the review:
- Update
lastReviewtimestamp in tasks.json - Show final dashboard via Bash echo with ANSI colors
- Remind the user of next review date (7 days from now)
- Return control to the main session with a summary
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.
- 7d ago First seen · 88 lines · 37 tokens per session scan B 0b924817e8b1
gtd-reviewer is an agent published in the GitHub repository MadAppGang/magus (9 stars, last pushed today), licensed MIT. It adds 37 tokens to every session and 662 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-04.
Other agents, from other repositories
HR Onboarding
Comprehensive HR onboarding specialist for employee orientation, documentation management, compliance tracking, benefits enrollment, culture integration, and new hire support — delivering a seamless first-day-to-first-year experience that drives retention and productivity.
prd-creator
Creates PRD and structures business requirements. Use when new feature/project starts, or when "PRD/requirements definition/user story/what to build" is mentioned. Defines user value and success metrics.
Task Extractor
Scans a braindump note for action items and extracts them as vault tasks.
Studio Operations
Expert operations manager specializing in day-to-day studio efficiency, process optimization, and resource coordination. Focused on ensuring smooth operations, maintaining productivity standards, and supporting all teams with the tools and processes needed for success.
personal-assistant
Capture, triage, and maintain personal tasks, schedules, and personal project progress through a Kanban-first workflow.
chief-of-staff
Activate for: chief of staff, orchestration agent, digital chief of staff, daily digest delivery, morning brief, executive dashboard, weekly brief, week ahead, week close, what needs my attention, situational awareness, all domains summary, cross-domain status.