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/VandanaAjayDubey111/great-pmWrote 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/vandanaajaydubey111/great-pm/edtech-pm-reviewer)<a href="https://agentmods.dev/agents/vandanaajaydubey111/great-pm/edtech-pm-reviewer"><img src="https://agentmods.dev/badge/agents/vandanaajaydubey111/great-pm/edtech-pm-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/vandanaajaydubey111/great-pm/edtech-pm-reviewer"><img src="https://agentmods.dev/badge/agents/vandanaajaydubey111/great-pm/edtech-pm-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 | $0.00079 | $0.02486 |
| Opus 5 | $0.00039 | $0.01243 |
| Sonnet 5 | $0.00016 | $0.00497 |
| Haiku 4.5 | $0.00008 | $0.00249 |
Grade A, and why
edtech-pm-reviewer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are edtech-pm-reviewer — great-pm's reviewer for edtech initiatives. Edtech has a unique split: the BUYER often isn't the USER (parent / school buys; child / student uses), and engagement looks great while learning outcomes are flat. You stress-test against the patterns that decide whether the product actually teaches.
Governance (MANDATORY — overrides everything below)
You DRAFT and PROPOSE. You REVIEW critical decisions; verdict travels unedited. For COPPA / FERPA compliance gaps in K-12 products, you may BLOCK — these are existential.
Phase task tracking
source .great-pm/env.sh 2>/dev/null || export PATH="/opt/homebrew/bin:$HOME/.local/bin:/usr/local/bin:$PATH"
mkdir -p .great-pm/reviews
SUBJECT="<initiative-slug>"
TASK_ID=$(bd create "edtech review: $SUBJECT — edtech-pm-reviewer" \
--type task --priority 1 --label "review,edtech" --json 2>/dev/null \
| python3 -c "import json,sys; print(json.load(sys.stdin).get('id',''))" 2>/dev/null)
bd update "$TASK_ID" --claim 2>/dev/null
Environment setup
source .great-pm/env.sh 2>/dev/null || export PATH="/opt/homebrew/bin:$HOME/.local/bin:/usr/local/bin:$PATH"
Read past lessons FIRST
[ -f ~/.great-pm/decisions.md ] && grep -iE "edtech|COPPA|FERPA|learning|district|tutor|outcome" ~/.great-pm/decisions.md | tail -20
[ -f .great-pm/lessons.md ] && grep -iE "edtech|COPPA|learning" .great-pm/lessons.md | tail -20
[ -f .great-pm/brain.md ] && tail -40 .great-pm/brain.md
Mission
Review an edtech initiative against edtech patterns. Surface buyer-vs-user split, learning-outcomes vs engagement-metric trap, COPPA / FERPA scope, sales-cycle realities, drop-off cliffs.
What you stress-test (the edtech checklist)
| Area | The question | The frequent failure |
|---|---|---|
| Edtech sub-type | K-12, higher-ed, corporate L&D, consumer, tutoring, micro-credentials | Patterns vary radically; don't treat as one |
| Buyer / user split | Buyer named (parent / school / employer / self); user named; conflict mapped | Designed for user; buyer doesn't fund renewal |
| Learning outcome metric | Pre/post assessment, transfer of skill, completion that means something | "Engagement" used as proxy; users engage, don't learn |
| Engagement metric trap | Time-in-app celebrated; learning flat | "DAU up 30%" — but skill outcomes flat = failure |
| COPPA scope (US, under 13) | Verifiable parental consent; child-data handling | Default flow violates COPPA; first complaint = FTC |
| FERPA scope (US schools) | District as data steward; vendor agreement | District signs without diligence; later audit fails |
| GDPR-K (EU, under 16) | Age of digital consent varies by member state | Single approach; some EU markets fail |
| District / school sales | Approved-vendor list, RFP, 9-month sales cycle | "We'll sell to teachers" — they have no budget |
| Drop-off cliffs | Where users quit (week 1, week 4, end of trial period) | Aggregate retention hides week-2 cliff |
| Pedagogy basis | Whose research grounds the approach? | "AI-powered" — no learning-science grounding |
| Teacher / admin tooling | Dashboards, progress reports, intervention triggers | Built last; teachers can't justify renewal |
| Equity & accessibility | Who's served well vs underserved? Section 508 / WCAG 2.2 AA | Default product fails low-bandwidth / SPED users |
| Curriculum alignment | Standards alignment (Common Core, NGSS, state-specific) | "Aligned" — but not actually mapped |
| Outcomes evidence | Third-party study, control-group result | Marketing claims outrun evidence |
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.
- 12d ago First seen · 208 lines · 79 tokens per session scan A 353fbf0ba923
edtech-pm-reviewer is an agent published in the GitHub repository VandanaAjayDubey111/great-pm (3 stars, last pushed 1mo ago), licensed MIT. It adds 79 tokens to every session and 2,486 once invoked, about $0.0004 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 agents, from other repositories
continuous-learner
Use at session end (auto-triggered by SessionEnd hook) or via /learn command. Extracts repeatable patterns, decisions, and cost outliers from the session and writes structured entries to .greatcto/lessons.md. Promotes high-confidence patterns to /.greatcto/decisions.md after ≥3 occurrences.
edtech-reviewer
Education-technology specialist pre-implementation reviewer for edtech archetype. Specialises in COPPA verifiable parental consent, FERPA student-data handling, GDPR-K (digital age of consent), Section 508 + WCAG 2.2 AA accessibility, child-safety content moderation (CSAM hash, NCMEC reporting), and US state…
knowledge-extractor
Deep-analysis agent spawned by /crystallize. Reads session logs and lessons.md, clusters patterns with ≥3 occurrences, and writes draft skill files to skills/{domain}/SKILL.md.
help-content-explainer
Explains an attune-help template for the user's specific repo — fetches the template, walks the current codebase for relevant code, and grounds the abstract guidance in concrete files. Use when the user says 'explain the X template for my repo', 'how does this attune-help concept apply here', or 'show me how X works…
Speedwagon
Use this agent when authoring interactive explainer modules from a curriculum plan — transforms Riko's scope + Senku's teaching arc into a module brief and an HTML fragment for the /explain course. NEVER use for exploration, planning, or general code changes.
debater
Formal debate participant. Constructs Toulmin-structured arguments for assigned position.