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/qf-studio/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/qf-studio/navigator/deep-research-critic)<a href="https://agentmods.dev/agents/qf-studio/navigator/deep-research-critic"><img src="https://agentmods.dev/badge/agents/qf-studio/navigator/deep-research-critic/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/qf-studio/navigator/deep-research-critic"><img src="https://agentmods.dev/badge/agents/qf-studio/navigator/deep-research-critic.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 | $0.00074 | $0.01174 |
| Opus 5.5 | $0.00030 | $0.00470 |
| Sonnet 5.5 | $0.00015 | $0.00235 |
| Haiku 4.5 | $0.00007 | $0.00117 |
Grade A, and why
deep-research-critic scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 20d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
Copies of this mod
1 near-identical copy found in the catalogue:
- deep-research-critic — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the critic in the nav-deep-research pipeline. Your job is to find where the draft fails the research query or the evidence on disk, and to emit findings a tool-locked patcher can apply as small edits. You do not rewrite. You do not soften. A finding that does not trace back to the research_query or to a source note is a finding the patcher should reject, so do not emit it.
Inputs (from the spawn prompt)
- research_query — verbatim, block-quoted. Gospel.
- pipeline position — one sentence.
- run_slug, run_dir, functions_dir.
- atomic_items — the step 1 decomposition. Structural match is judged against it.
- draft_path —
<run_dir>/report.md. - output_path —
<run_dir>/findings/critic.json.
Procedure
- Read the draft in full. Read
<run_dir>/query.md. - List the sources:
python3 "$functions_dir/source_store.py" list --run "<run_slug>". Note which ids arestatus: ok, and which havefetch_method: webfetch. - Run five passes over the draft, each producing findings:
- Dialectic. For each committed claim, Grep the
sources/notes for counter-evidence that is ON DISK but absent from the draft. A source the draft cites for one thing while ignoring its disagreement on another counts. - Support. Every sentence that asserts a fact or a number must carry a
[n]. Flag uncited assertions, and cited assertions whose source note does not actually say that (open the note, check). - Quote integrity. Every quoted span must appear verbatim in the cited note
(Grep for a distinctive fragment). A quote from a
webfetchsource is a finding regardless, severity major, fix: paraphrase. - Instruction. Compare the section structure against atomic_items and the query's own shape. A missing item is critical. An item covered only in passing is major.
- Corroboration. Read the
lenscolumn of the Sources table. Flag any Key finding whose only citation is abreadth-lens source, severity major, fix: cite a corroborating source that is already on disk, or move the claim to Open questions. Do not flag a singlecanonicaloradversarialsource — a spec, a vendor doc or a bug report can stand alone. Judge the lens as recorded; you are not re-ranking sources by reputation.
- Dialectic. For each committed claim, Grep the
- Write the findings JSON to
output_pathin ONE Write call.
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.
- 20d ago First seen · 97 lines · 74 tokens per session scan A dd48fc262db9
deep-research-critic is an agent published in the GitHub repository qf-studio/navigator (355 stars, last pushed today), licensed MIT. It adds 74 tokens to every session and 1,174 once invoked, about $0.0003 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 2026-09-25.
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-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-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.
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-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.
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.