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 hanlulong/econ-paper-review-skill --skill econ-reviewgit clone --depth 1 https://github.com/hanlulong/econ-paper-review-skillWrote 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/hanlulong/econ-paper-review-skill/econ-review)<a href="https://agentmods.dev/skills/hanlulong/econ-paper-review-skill/econ-review"><img src="https://agentmods.dev/badge/skills/hanlulong/econ-paper-review-skill/econ-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/hanlulong/econ-paper-review-skill/econ-review"><img src="https://agentmods.dev/badge/skills/hanlulong/econ-paper-review-skill/econ-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 | $0.00150 | $0.04625 |
| Opus 5.5 | $0.00060 | $0.01850 |
| Sonnet 5.5 | $0.00030 | $0.00925 |
| Haiku 4.5 | $0.00015 | $0.00462 |
Grade A, and why
econ-review 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 2mo 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.
The source is not reproduced here
A licence we could not identify
The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.
What ships with it
60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- .claude-plugin/plugin.json 659 B
- .codex-plugin/plugin.json 1.7 KB
- agents/openai.yaml 487 B
- assets/agent-response.schema.json 4.9 KB
- assets/analytical-audit.schema.json 8.1 KB
- assets/candidates.schema.json 4.9 KB
- assets/claims.schema.json 35 KB
- assets/computations.schema.json 3.0 KB
- assets/coverage.schema.json 9.3 KB
- assets/external-sources.schema.json 43 KB
- assets/figures.schema.json 8.7 KB
- assets/finalization.schema.json 1.3 KB
- assets/findings.schema.json 11 KB
- assets/pdf-ingestion.schema.json 15 KB
- assets/pdf-reconciliation-decisions.schema.json 2.5 KB
- assets/review-actions.schema.json 9.3 KB
- assets/review-desk.zip 1203 KB
- assets/review-manifest.schema.json 1.4 KB
- assets/review-report-template.tex 6.4 KB
- assets/revision-tasks.schema.json 3.9 KB
- assets/round-reconciliation.schema.json 5.3 KB
- assets/run.schema.json 16 KB
- assets/source-manifest.schema.json 3.5 KB
- assets/synthesis.schema.json 4.1 KB
- assets/tables.schema.json 9.1 KB
- assets/verification.schema.json 1.8 KB
- assets/writing.schema.json 18 KB
- LICENSE 4.6 KB
- references/analytical-ledgers.md 12 KB
- references/argument-evidence-audit.md 15 KB
- references/comment-style.md 13 KB
- references/design-audit.md 14 KB
- references/design-presets.md 6.4 KB
- references/editorial-synthesis.md 9.7 KB
- references/exhaustive-audit.md 18 KB
- references/figure-audit.md 10 KB
- references/gates/did.md 5.6 KB
- references/gates/iv.md 4.6 KB
- references/gates/rdd.md 4.6 KB
- references/inference-audit.md 12 KB
- references/literature-frontier.md 25 KB
- references/output-contracts.md 53 KB
- references/pdf-backends.md 7.8 KB
- references/pdf-ingestion.md 20 KB
- references/reader-claim-audit.md 13 KB
- references/reconstruction-protocol.md 13 KB
- references/red-lines.md 4.8 KB
- references/replication-audit.md 6.6 KB
- references/research-integrity-audit.md 5.4 KB
- references/review-actions-handoff.md 5.9 KB
- references/revision-cycle.md 9.4 KB
- references/table-audit.md 4.9 KB
- references/verification-protocol.md 15 KB
- references/workflow.md 14 KB
- references/writing-reference-venue-audit.md 11 KB
- requirements-core.txt 152 B
- requirements-docling.txt 42 B
- requirements-markitdown.txt 48 B
- requirements-mathpix.txt 43 B
- scripts/capture_external_source.py 21 KB runs code
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.
- 2mo ago First seen · 148 lines · 150 tokens per session scan A cc7640fc7dce
econ-review is a skill published in the GitHub repository hanlulong/econ-paper-review-skill (35 stars, last pushed 2mo ago), with no licence file. It adds 150 tokens to every session and 4,625 once invoked, about $0.0006 per session on Opus 5.5. 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 2026-08-30.
econ-review compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| econ-reviewhanlulong/econ-paper-review-skill | Skill | 35 | 2mo ago | none | A | 150 | Claude Code, Codex |
| audit-reproducibilitypedrohcgs/claude-code-my-workflow | Skill | 1.7k | 2d ago | MIT | A | 54 | Claude Code |
| review-paperpedrohcgs/claude-code-my-workflow | Skill | 1.7k | 2d ago | MIT | A | 0 | Claude Code |
| diagnosepedrohcgs/claude-code-my-workflow | Skill | 1.7k | 2d ago | MIT | A | 0 | Claude Code |
| grant-proposalpedrohcgs/claude-code-my-workflow | Skill | 1.7k | 2d ago | MIT | A | 131 | Claude Code |
| slide-excellencepedrohcgs/claude-code-my-workflow | Skill | 1.7k | 2d ago | MIT | A | 94 | Claude Code |
| capture-environmentpedrohcgs/claude-code-my-workflow | Skill | 1.7k | 2d ago | MIT | A | 139 | Claude Code |