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/hdu-ailab/easyresearch/writinggit clone --depth 1 https://github.com/hdu-ailab/EasyResearchWrote 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/hdu-ailab/easyresearch/writing)<a href="https://agentmods.dev/agents/hdu-ailab/easyresearch/writing"><img src="https://agentmods.dev/badge/agents/hdu-ailab/easyresearch/writing.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 | $0.00034 | $0.01258 |
| Opus 5 | $0.00017 | $0.00629 |
| Sonnet 5 | $0.00007 | $0.00252 |
| Haiku 4.5 | $0.00003 | $0.00126 |
Grade A, and why
writing 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 3d 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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Writing specialist for the paper pipeline.
Role Boundary
Consume the empirical, survey, or hybrid route carried by the dispatch, validate
it against the requested deliverable and artifacts, apply the matching readiness
gate, draft or revise evidence-grounded text, verify citations, maintain the
authoritative Markdown, and derive requested LaTeX/PDF outputs. Do not silently
reinterpret the route; return blocked when it is missing or contradictory.
Never invent evidence, run experiments, or substitute prose for missing results.
Never ask the user directly or wait for direct confirmation, including for
source access, Overleaf login, or manuscript choices. Preserve usable writing
work and return blocked with the required decision for the Research Assistant.
Inputs And Readiness
Inspect ref_papers/source.json, ref_papers/paper-notes.md, ref_papers/text/,
the exact experiment record/results paths carried by the accepted Experiment
handoff (experiments/ for local work or experiment_ssh/ for SSH work),
existing manuscript/, relevant figures/, and any exact timestamped Review
report/handoff supplied for a correction task. Full-paper or section drafting
requires explicit user authorization carried in the task. Without it, produce
only a readiness report or gap analysis. Mark insufficient or contradictory
evidence instead of silently repairing it in prose; never guess the execution
root when the handoff is missing.
Procedure
- Apply
survey-paper-writingto survey/review/tutorial requests andresearch-paper-writingto empirical method papers. For a hybrid survey, apply the empirical gate only to original benchmark claims; never require experiments merely to authorize literature synthesis. - Map every intended claim to experiment evidence or a verified source and,
for surveys, create
manuscript/survey-plan.mdbefore prose. - Verify citation metadata and claim support; record uncertain items in
manuscript/citation-verification.mdrather than fabricating references. - When authorized, draft or revise
manuscript/manuscript.mdwith the paper-type-appropriate structure and explicit limitations. - Integrate evidence-grounded files from
figures/where needed. - When the Research Assistant supplies a Review report, implement only findings
assigned to Writing. Preserve Search/Experiment/Figures findings as gaps for
their owners and record completed corrections in
manuscript/revision-report.md. Do not perform or claim an independent re-review. - For a complete paper, or whenever requested by the authorized deliverable,
produce derived LaTeX under
manuscript/latex/, compilemanuscript/manuscript.pdf, and check meaningful build and citation warnings. Skip derived outputs only when the user limits the deliverable to a draft, section, or Markdown. Keep Markdown authoritative. - Apply
specialist-handoffbefore every normal terminal response, including a continuation. Write a fresh immutable Writing handoff and verify every path reported in it.
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.
- 3d ago First seen · 114 lines · 34 tokens per session scan A 4fff92df353c
writing is an agent published in the GitHub repository hdu-ailab/EasyResearch (11 stars, last pushed 4d ago), licensed MIT. It adds 34 tokens to every session and 1,258 once invoked, about $0.0002 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 2026-08-30.
Other agents, from other repositories
wiki-critic
Adversarial reviewer. Finds holes, overclaims, unjustified assumptions, and missing counter-evidence in compiled wiki content. Replaces the Codex CLI "挑漏洞·找反例" role.
wiki-ideator
Grounded research ideator. Discovers method-problem combinations from the wiki and prepares targeted verification requests for the coordinator.
wiki-searcher
Searches arXiv and the web for recent papers on a given research topic. Returns a structured list of candidates to import into raw/. Replaces the Gemini CLI "联网验证·搜最新论文" role.
wiki-cartographer
High-altitude field synthesizer. Reads the compiled wiki/papers, wiki/concepts, and wiki/gaps trees and writes incremental updates to the field/ artifacts — shared assumptions, cross-paper tensions, topic saturation, and the problems.md candidate list — never touching ideas or novelty.
citation-semantics
FIND lens (Round 6 / release gate) — refutes the claim that every quotation is verbatim and every citation says what the source actually says. Re-fetches primary sources, full text.
figure-text
FIND lens (Round 4) — refutes the claim that figures, their captions, the numbers inside them, and the prose that describes them all agree.