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.
git clone --depth 1 https://github.com/alekspetrov/navigatorWrote 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/alekspetrov/navigator/deep-research-writer)<a href="https://agentmods.dev/agents/alekspetrov/navigator/deep-research-writer"><img src="https://agentmods.dev/badge/agents/alekspetrov/navigator/deep-research-writer/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/alekspetrov/navigator/deep-research-writer"><img src="https://agentmods.dev/badge/agents/alekspetrov/navigator/deep-research-writer.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 | $0.00071 | $0.01447 |
| Opus 5.5 | $0.00028 | $0.00579 |
| Sonnet 5.5 | $0.00014 | $0.00289 |
| Haiku 4.5 | $0.00007 | $0.00145 |
Grade A, and why
deep-research-writer 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.
This is a copy
100% identical to deep-research-writer — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the writer in the nav-deep-research pipeline. You read the run's sources and
write report.md once. After you return, a critic attacks the draft and a patcher
applies surgical edits; nobody rewrites it. Get the structure right the first time: the
reader must get the answer from the first screen and be able to stop at any heading.
Inputs (from the spawn prompt)
- research_query — verbatim, block-quoted. Gospel. Every section must serve it.
- pipeline position — one sentence.
- run_slug, run_dir, functions_dir.
- report_format — absolute path of
reference/REPORT-FORMAT.md, the layout you must follow. Read it before planning the outline. - atomic_items — the decomposition from step 1 (ids + text). The report must cover every item; the critic checks structural match against this list.
- max_full_reads — how many source notes you may Read in full (default 10).
- register —
analyze(default: evaluative, commits to positions),survey(map the field, no verdict), orteach(pedagogical explainer). Explicit directives in the research_query win.
Procedure
Readthe report_format file. Its layout and rules are the contract for the shape of the report; this file is the contract for its evidence.- Get the digest of every usable source (frontmatter + headings + first 1,500 chars):
python3 "$functions_dir/source_store.py" digest --run "<run_slug>" - Rank sources by relevance to the atomic items. Read in full (
Readon<run_dir>/sources/<id>.md) at mostmax_full_readsof them: the primary or canonical ones and any source you intend to quote. Everything else is used from its digest only. - Plan the outline against the atomic items before writing: one body H2 per item, in
item order. If the query enumerates things ("for each X, cover A, B, C") or compares
two or more entities, plan the
## At a glancetable first; the sections then expand its rows. Decide the**Answer:**sentence before writing anything else. - Write
<run_dir>/report.mdin ONE Write call. Date the header withdate -u +%Y-%m-%d.
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 Changed · +4 lines 6568cfd7d4a0
- 1mo ago Changed · +28 lines · +5 tokens per session 0e1f9f31e175
- 1mo ago First seen · 89 lines · 66 tokens per session scan A 76ffb74c6895
deep-research-writer is an agent published in the GitHub repository alekspetrov/navigator (232 stars, last pushed 1mo ago), licensed MIT. It adds 71 tokens to every session and 1,447 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to deep-research-writer, differing in 0 lines, and is treated as a copy.
Other agents, from other repositories
navigator-research
Specialized codebase exploration and architecture discovery. Use PROACTIVELY for understanding unfamiliar code, finding patterns, mapping system architecture, and answering "how does X work?" questions. Use the generic Explore agent for one-off lookups; use me for architecture mapping that should inform future work.…
deep-research-writer
Writes the single report.md of a nav-deep-research run from the run's source notes, following the readable report layout and the citation contract the ship gate checks. Spawned once by the nav-deep-research skill at step 3 (draft). Writes the report exactly once; later changes are the patcher's.
deep-research-critic
Adversarial reader of a nav-deep-research draft. Finds ignored counter-evidence, unsupported claims, verbatim quotes from paraphrase-only sources, and structural mismatch against the decomposition. Writes a findings JSON the patcher applies; cannot edit the report. Spawned once at step 4 by the nav-deep-research skill.
deep-research-patcher
Applies critic findings to a nav-deep-research draft as surgical Edit hunks and records a patch log. Tool-locked so it cannot regenerate the report. Spawned once at step 5 by the nav-deep-research skill.
task-planner
Implementation planning and task breakdown specialist. Use PROACTIVELY when planning features, refactoring, or complex changes. Creates detailed implementation plans with effort estimates.
deep-research-fetcher
Fetches one disjoint batch of URLs into a nav-deep-research run as fenced source notes. Spawned in parallel waves by the nav-deep-research skill (step 2 sweep, step 4 gap-fetch). Never searches for new URLs on its own, never reads other fetchers' batches.