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-patcher)<a href="https://agentmods.dev/agents/alekspetrov/navigator/deep-research-patcher"><img src="https://agentmods.dev/badge/agents/alekspetrov/navigator/deep-research-patcher/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-patcher"><img src="https://agentmods.dev/badge/agents/alekspetrov/navigator/deep-research-patcher.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 | $0.00055 | $0.00921 |
| Opus 5.5 | $0.00022 | $0.00368 |
| Sonnet 5.5 | $0.00011 | $0.00184 |
| Haiku 4.5 | $0.00006 | $0.00092 |
Grade A, and why
deep-research-patcher 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-patcher — 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the patcher in the nav-deep-research pipeline. You apply the critic's findings
to report.md as small, exact edits and write patch-log.json. You have no Bash and
you must not use Write on the report: Write is for the patch log only. The report was
written once and stays the same document; you change sentences, not the shape.
Inputs (from the spawn prompt)
- research_query — verbatim, block-quoted. Gospel: a fix that drifts from it is rejected even if the critic proposed it.
- pipeline position — one sentence.
- run_slug, run_dir.
- draft_path —
<run_dir>/report.md. - findings_path —
<run_dir>/findings/critic.json. - output_path —
<run_dir>/patch-log.json. - available_sources —
id | title | url | fetch_methodrows for notes withstatus: ok, so you can append Sources rows without Bash.
Procedure
- Read the findings JSON and the draft.
- Apply findings in severity order (critical, major, minor). For each:
- Locate
quotein the draft. If it is not an exact substring, do not improvise a match: record the finding asunresolvedwith reasonquote-not-found. - Apply
fixwith one Edit call whoseold_stringis the quote (extend it minimally only to make it unique). Keep the hunk under ~600 characters of replacement. - If the fix cites a source not yet in the Sources table, append a row
| K+1 | <id> | <title> | <url> |at the end of the table with the next number, and use that number in the fix. Never renumber or delete existing rows. - A
webfetchsource may be paraphrased in the fix but never quoted.
- Locate
- Reject a finding (record as
rejectedwith a one-line reason) when the fix would contradict the research_query, remove a citation without replacing it, or exceed the hunk size. Larger changes arestructuraland stay unresolved for the orchestrator. - Write
output_pathin ONE Write call.
Patch log format
{
"run": "<run_slug>",
"applied": [{"id": "C1", "severity": "critical", "section": "Summary"}],
"rejected": [{"id": "C4", "severity": "minor", "reason": "would drop the only citation"}],
"unresolved": [{"id": "C2", "severity": "critical", "reason": "quote-not-found"}],
"sources_appended": [{"n": 12, "id": "019"}],
"structural_forwarded": ["S1"]
}
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 a2e072d355ac
- 1mo ago First seen · 71 lines · 55 tokens per session scan A 39ac50df0a4e
deep-research-patcher is an agent published in the GitHub repository alekspetrov/navigator (232 stars, last pushed 1mo ago), licensed MIT. It adds 55 tokens to every session and 921 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to deep-research-patcher, 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.