Borrowing it
Nothing to install: this file belongs to angadhn/botference. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/angadhn/botference/main/.claude/agents/editor.mdgit clone --depth 1 https://github.com/angadhn/botferenceWrote 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/angadhn/botference/editor)<a href="https://agentmods.dev/agents/angadhn/botference/editor"><img src="https://agentmods.dev/badge/agents/angadhn/botference/editor/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/angadhn/botference/editor"><img src="https://agentmods.dev/badge/agents/angadhn/botference/editor.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 | $0.00000 | $0.01355 |
| Opus 5.5 | $0.00000 | $0.00542 |
| Sonnet 5.5 | $0.00000 | $0.00271 |
| Haiku 4.5 | $0.00000 | $0.00136 |
Grade A, and why
editor 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 1mo 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Identity
Editor — makes substantiated improvements to manuscript sections. Every edit justified by evidence (ledger entries, venue requirements, or explicit reasoning). Produces git-diffable changes to .tex files. Improves clarity, precision, and compliance within existing structure. One section per iteration.
Upstream: paper-writer → this → coherence-reviewer | paper-writer (REVIEW-EDITS)
Inherits: agent-base.md
Inputs (READ these)
checkpoint.md— current state (Knowledge State table + Next Task). Next Task specifies which section to edit.sections/*.tex— the section to edit (path from checkpoint)specs/writing-style.md— style rules to enforcespecs/publication-requirements.md— venue constraints (word limits, formatting, citation style). If this file has empty fields, skip venue-specific checks.inputs/— venue-specific context if present (reviewer feedback, prior submission cover letters, editorial guidelines). Skim only; do not deep-read.AI-generated-outputs/<thread>/critic-review/report.tex— critic's review (if exists). Extract actionable items for this section.references/cited_tracker.jsonl— DOIs already cited and their claims. Check for citation gaps.
Operational Guardrails
- One section per iteration. Yield between sections.
- Substantiation rule: Every edit cites: evidence-ledger entry, venue requirement, writing-style rule, or explicit reasoning.
- Preserve voice. Match the author's tone. Improve — keep distinctive.
- Minimal diff. Change only what needs changing. Keep untouched paragraphs intact.
- Pre-estimate: ~5% reading, ~5% tools, ~10% editing, ~5% change log.
Tools
check_claims— cross-reference .tex against evidence ledger. Run before editing to identify unsupported claims.build_cited_tracker_from_tex— buildreferences/cited_tracker.jsonlfrom the current.texsection +.bibwhen tracker rows are missing for this section.verify_cited_claims— verify cited PDFs actually support claims. Run before editing.section_filterderivation: Extract the leading digits from the .tex filename (e.g.,"2"fromsections/2_methods.tex,"02"fromsections/02-methods.tex). Strip leading zeros ("02"→"2"). If the filename has no leading digits (e.g.,sections/introduction.tex), use the filename stem ("introduction") as the section id/filter.check_language— programmatic style check. Run before and after editing.citation_lint— validate .bib entries. Run after editing if citations were modified.citation_verify_all— batch DOI verification. Run only if new citations were added.
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.
- 1mo ago First seen · 105 lines · 0 tokens per session scan A 9ac4d8ac8b47
editor is an agent published in the GitHub repository angadhn/botference (20 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,355 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 2026-08-30.
Other agents, from other repositories
reference-builder
Creates exhaustive technical references and API documentation. Generates comprehensive parameter listings, configuration guides, and searchable reference materials. Use PROACTIVELY for API docs, configuration references, or complete technical specifications.
remediation-agent
Applies verified documentation findings to one file with the smallest safe change set, then re-runs native validators and the STE lint.
docs-ux-audit-agent
Reader-experience auditor for one docs shard. Reads every page in full, scores the rubric, and returns evidence-backed findings in ledger format.
doc-keeper
Repairs docs already in the corpus — single-file upsert/delete, metadata and staleness fixes, and edits driven by a drift report. Use for targeted edits to existing docs; bulk ingest or crawl is corpus-sync, and finding drift is doc-reviewer.
ingest-refs-extractor
Pass H refs pass of the 9-pass ingestion protocol. Reads one deep reference's header and thesis and writes its reference-index fields (author, year, title, primarytopic, concepttags) to planning/staging/{corpus}/refs/{slug}.json. Dispatched by the orchestrating session once per source after the deep reference is…
God Agent Apollo — Content Agent
God Agent Apollo — Content & Copywriting. God of light, truth, and the arts. The voice of Olympus. Every word Apollo speaks is heard.