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 skills add andrehuang/researcher-pack --skill weekly-reviewgit clone --depth 1 https://github.com/andrehuang/researcher-packWrote 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/skills/andrehuang/researcher-pack/weekly-review)<a href="https://agentmods.dev/skills/andrehuang/researcher-pack/weekly-review"><img src="https://agentmods.dev/badge/skills/andrehuang/researcher-pack/weekly-review/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/skills/andrehuang/researcher-pack/weekly-review"><img src="https://agentmods.dev/badge/skills/andrehuang/researcher-pack/weekly-review.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 | $0.00004 | $0.01715 |
| Opus 5 | $0.00002 | $0.00857 |
| Sonnet 5 | $0.00001 | $0.00343 |
| Haiku 4.5 | $0.00000 | $0.00171 |
Grade B, and why
weekly-review 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 10d 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.
Strips warnings and disclaimersmediumAnti-refusal
Omitting safety caveats hides risk from the user and is a common jailbreak preamble.
- **Don't moralize about streaks.** Report them factually. Some weeks are for thinking, not training. How it starts
The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Weekly Review — Research Digest
You produce a structured research digest that helps the researcher see their trajectory, identify gaps, and set priorities. This is reflection and planning, not just reporting.
ultrathink
Context Loading
Read all sources in parallel:
events.jsonl— filter to the review period (default: last 7 days). Count events by type..claude/research-state.yaml— current gym, wiki, and session stateIDEAS.md— check for changes (git diff if available), note new items- Wiki pages — Glob all pages, check
last_revieweddates, count by type. Includewiki/research-evaluations/in the counts (these are persisted verdicts from/research-companion). - Mental Gym status — run
cd mental-gym && .venv/bin/mental-gym statusto get current mastery data - Git log — run
git log --oneline --since="7 days ago"for commit activity .review/directory — check for unresolved academic review findings
If a date range is provided in $ARGUMENTS (e.g., "last 14 days", "March 1-7"), adjust the filter period accordingly. Default is 7 days from today.
Report Structure
Present the digest in this format:
Weekly Research Digest — [Start Date] to [End Date]
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Activity Summary
Papers ingested: [N] ([list titles if any])
Training sessions: [N] ([total exercises], avg score [X])
Wiki pages updated: [N]
Experiments run: [N]
Writing reviews: [N] ([total findings])
IDEAS.md updates: [N]
Commits: [N]
Knowledge Growth
Wiki: [total pages] pages ([+N new] this week, includes research-evaluations/)
Topics mastered (>70%): [list or "none yet"]
Topics improved: [list with deltas, e.g., "validation-levels: 0% → 35%"]
Topics declining: [list with days since last review]
New concepts added: [list]
Decisions made this week
[list each research-evaluations/ page touched this week with its verdict,
e.g. "agent-populations-for-polling — PURSUE",
"simulators-as-survey-instruments — PARK (revisit: Q3 data release)"]
[omit this block if empty]
Research Trajectory
Active threads: [from IDEAS.md and recent events]
Decisions made: [any PURSUE/PARK/KILL from research-companion]
Dots connected: [any new connections identified]
Questions answered: [any wiki queries promoted]
Health Checks
Stale wiki pages (>60 days): [list]
Orphan wiki pages: [list]
Unresolved review findings: [count and file]
Training streak: [N days, or "broken — last session [date]"]
IDEAS.md last updated: [date]
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.
- 10d ago First seen · 148 lines · 0 tokens per session scan B f8b589236140
weekly-review is a skill published in the GitHub repository andrehuang/researcher-pack (49 stars, last pushed 4mo ago), licensed MIT. It adds 4 tokens to every session and 1,715 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it B with 1 finding (strips warnings and disclaimers). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…