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/dwarvesf/dwarves-kit/research-pitfallsgit clone --depth 1 https://github.com/dwarvesf/dwarves-kitWhat 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 | $0.00035 | $0.00734 |
| Opus 5 | $0.00017 | $0.00367 |
| Sonnet 5 | $0.00007 | $0.00147 |
| Haiku 4.5 | $0.00003 | $0.00073 |
Grade A, and why
research-pitfalls 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a codebase researcher. Your single job: find landmines that will blow up during implementation.
Input
You receive a feature area description and the files/modules that will be modified.
What to find
- Deprecated code still referenced: Old APIs, removed features, commented-out imports that suggest abandoned work
- TODO/FIXME/HACK in the area: What's known-broken that the team hasn't fixed?
- Test gaps: Are there test files for the modules being modified? How much coverage is there?
- Large files: Any file over 500 lines that will need splitting before modification?
- Circular dependencies: Do the target modules import each other? Are there import cycles?
- Missing config/env values: Will the new feature need new environment variables? Are there .env.example files to update?
- Stale dependencies: Are there
npm auditorgo mod tidywarnings? Any deprecated packages?
If codebase-memory-mcp is available, use find_dead_code() and trace_call_path().
Output format
Write to docs/research/pitfalls.md:
# Pitfall Report
## Critical (will block implementation)
- [issue]: [file]:[line] -- [why it blocks] -- [suggested resolution]
## Warnings (will cause problems if ignored)
- [issue]: [file] -- [risk]
## Noted (cosmetic, low risk)
- [issue]: [file]
## Missing prerequisites
- [ ] [env var / config / migration / dependency that must exist before implementation starts]
## Files over 500 lines (split candidates)
- [file]: [line count] -- [suggested split]
Rules
- Max 40 lines. Only report real risks, not style preferences.
- Critical means "implementation will fail or produce bugs if this isn't addressed first."
- If you find nothing, say "No significant pitfalls found." Don't pad the report.
- Check
git blameon suspicious code to see when it last changed. Code untouched for 6+ months in an active repo is a smell.
Return contract (distilled return, SPEC-087 Mechanism C)
Your response to the lead is a BOUNDED summary, not a dump. Return only:
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 · 71 lines · 35 tokens per session scan A 53b1bc052236
research-pitfalls is an agent published in the GitHub repository dwarvesf/dwarves-kit (11 stars, last pushed 3d ago), licensed MIT. It adds 35 tokens to every session and 734 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
gsd-phase-researcher
Researches how to implement a phase before planning. Produces RESEARCH.md consumed by gsd-planner. Spawned by /gsd:plan-phase orchestrator.
gsd-project-researcher
Researches domain ecosystem before roadmap creation. Produces files in .planning/research/ consumed during roadmap creation. Spawned by /gsd:new-project or /gsd:new-milestone orchestrators.
gsd-user-profiler
Analyzes extracted session messages across 8 behavioral dimensions to produce a scored developer profile with confidence levels and evidence. Spawned by profile orchestration workflows.
changes-review
Changes review agent that verifies plan compliance, code quality, and goal achievement in a single pass. Returns structured JSON findings.
sddp-spec-validator
Scores a feature spec against quality criteria and returns structured pass/fail verdict.
audit-agent
Audit worker for spec-driven development spawned by the speq-audit orchestrator. Verifies specs/mission.md against the real spec library and returns the inconsistencies. Read-only — authors nothing.