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/mereditharmcgee/the-commons/known_tech_debtgit clone --depth 1 https://github.com/mereditharmcgee/the-commonsWrote 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/mereditharmcgee/the-commons/known_tech_debt)<a href="https://agentmods.dev/agents/mereditharmcgee/the-commons/known_tech_debt"><img src="https://agentmods.dev/badge/agents/mereditharmcgee/the-commons/known_tech_debt.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 | $0.00000 | $0.04481 |
| Opus 5 | $0.00000 | $0.02240 |
| Sonnet 5 | $0.00000 | $0.00896 |
| Haiku 4.5 | $0.00000 | $0.00448 |
Grade A, and why
KNOWN_TECH_DEBT 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 today.
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 — 364 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Known Tech Debt — The Commons
Implicit tech debt made explicit so an agent doing a sweep doesn't have to discover it from scratch. Ranked by severity (HIGH → LOW). Update as items are paid down or new ones surface.
If you're picking a first task, the HIGH items are where to start.
HIGH — load patterns at risk of the admin-dashboard hang — RESOLVED 2026-06-10
All four audit findings fixed (audit:
.planning/unbounded-reads-audit-2026-06-09.md;
spec + plan in docs/superpowers/{specs,plans}/2026-06-10-audit-followups*):
- A1 —
Utils.getAllPosts()pagination loop: deleted. Correction found during implementation: discussions.html is a redirect stub to interests.html and no page loaded discussions.js — the loop was a dead footgun that never ran in production (see the LOW entry below). - B1 — interest-page counts wrong: fixed via the new
discussion_statsview (security_invoker, visible-posts semantics; patchsql/patches/discussion-stats-view.sql). Verified live: "Open Letters" showed 17 responses; true count 127. - C1 — public postcards wall at the 1,000-row cap (793 when fixed):
server-side pagination, PAGE_SIZE 20, totals via the new
Utils.getCount()HEAD helper; Copy Context fetches its own recent-15. - C2 — admin postcards tab: count-and-cap 200 (
fac1167pattern);stat-postcardsnow exempt fromupdateStats()like stat-posts.
The 1,000-row-cap fact and the flag-only D-list (per-thread getPosts, admin render-all tabs under 1k, news.js N+1, etc.) stay documented in the audit doc — none urgent.
LOW — discussions.html is a redirect stub; js/discussions.js is orphaned — RESOLVED 2026-07-09
Resolved: js/discussions.js deleted (grep confirmed zero HTML pages referenced it). The discussions.html redirect stub stays — inbound links exist in the wild. CLAUDE.md's page map notes the stub.
HIGH — Posts tab has no search — RESOLVED 2026-06-10
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.
- today Changed · +24 lines e65a496818df
- 4d ago First seen · 340 lines · 0 tokens per session scan A e239b2c04b33
KNOWN_TECH_DEBT is an agent published in the GitHub repository mereditharmcgee/the-commons (3 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,481 tokens. 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
trinity-verify
Cross-provider, lens-judged verifier. Invoke as the CHECKER in any loop: it gets a second opinion from a DIFFERENT lab (Claude/GPT/Gemini) on the user's own subscriptions, graded by their taste. Use after a maker agent produces a change, plan, or 'done' claim — especially for risky or irreversible work.
index
Browse built-in Agent Framework capabilities for multimodal input, tools, retrieval, evaluation, security, and autonomous execution.
cloud_architect
Cloud architecture specialist for AWS, GCP, and Azure topology design, IaC patterns, multi-region resilience, and cost/security trade-offs. Use when the task requires designing a cloud deployment, reviewing IaC for best practices, or evaluating multi-region/DR strategies. For example: choosing between ECS and EKS…
index
Use NodeTool from an agent or automation: install it, discover nodes, run workflows, and inspect jobs.
image-generator
Use this agent when the conversation context involves generating or editing images. This agent should be used proactively when image creation would help the user's task. It also covers named product and brand assets, which users rarely call "images": app icons, bot avatars, logos, favicons, hero images, banners…
impeccable-agent
Autonomous executor for non-interactive impeccable commands. Runs audit, polish, harden, layout, typeset, and other automatable design operations without user interaction.