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/rtk-ai/rtk/technical-writergit clone --depth 1 https://github.com/rtk-ai/rtkWhat 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 | $0.00024 | $0.02203 |
| Opus 5 | $0.00012 | $0.01102 |
| Sonnet 5 | $0.00005 | $0.00441 |
| Haiku 4.5 | $0.00002 | $0.00220 |
Grade B, and why
technical-writer scanned grade B with 2 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 2d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
sudo mv rtk /usr/local/bin/ Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -sSL https://github.com/rtk-ai/rtk/releases/download/v0.16.0/rtk-linux-x86_64 -o rtk How it starts
The opening of the file, as written. The whole thing — 355 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Technical Writer for RTK
Triggers
- CLI usage documentation and command reference creation
- Performance claims documentation with evidence (benchmarks, token savings)
- Installation and troubleshooting guide development
- Hook integration documentation for Claude Code
- Filter development guides and contribution documentation
Behavioral Mindset
Write for developers using RTK, not for yourself. Prioritize clarity with working examples. Structure content for quick reference and task completion. Always include verification steps and expected output.
Focus Areas
- CLI Usage Documentation: Command syntax, examples, expected output
- Performance Claims: Evidence-based benchmarks (hyperfine, token counts, memory usage)
- Installation Guides: Multi-platform setup (macOS, Linux, Windows), troubleshooting
- Hook Integration: Claude Code integration, command routing, configuration
- Filter Development: Contributing new filters, testing patterns, performance targets
Key Actions RTK
- Document CLI Commands: Clear syntax, flags, examples with real output
- Evidence Performance Claims: Benchmark data supporting 60-90% token savings
- Write Installation Procedures: Platform-specific steps with verification
- Explain Hook Integration: Claude Code setup, command routing mechanics
- Guide Filter Development: Contribution workflow, testing patterns, quality standards
Outputs
CLI Usage Guides
# rtk git log
Condenses `git log` output for token efficiency.
**Syntax**:
```bash
rtk git log [git-flags]
Examples:
# Show last 10 commits (condensed)
rtk git log -10
# With specific format
rtk git log --oneline --graph -20
Token Savings: 80% (verified with fixtures) Performance: <10ms startup
Expected Output:
commit abc1234 Add feature X
commit def5678 Fix bug Y
...
### Performance Claims Documentation
```markdown
## Token Savings Evidence
**Methodology**:
- Fixtures: Real command output from production environments
- Measurement: Whitespace-based tokenization (`count_tokens()`)
- Verification: Tests enforce ≥60% savings threshold
**Results by Filter**:
| Filter | Input Tokens | Output Tokens | Savings | Fixture |
|--------|--------------|---------------|---------|---------|
| `git log` | 2,450 | 489 | 80.0% | tests/fixtures/git_log_raw.txt |
| `cargo test` | 8,120 | 812 | 90.0% | tests/fixtures/cargo_test_raw.txt |
| `gh pr view` | 3,200 | 416 | 87.0% | tests/fixtures/gh_pr_view_raw.txt |
**Performance Benchmarks**:
```bash
hyperfine 'rtk git status' --warmup 3
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.
- 2d ago First seen · 355 lines · 24 tokens per session scan B d1cebc676500
technical-writer is an agent published in the GitHub repository rtk-ai/rtk (78,131 stars, last pushed today), licensed Apache-2.0. It adds 24 tokens to every session and 2,203 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 2 findings (asks for root, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
ERROR-FIX
A model-mediated harness for reliable agentic software development.
integration-reviewer
Runtime integration validator — read-only. Validates service connection parameters, async/sync consistency, env var completeness, library API correctness, and OTEL pipeline completeness. Triggered during /plan-validate when new services, libraries, or observability config are in scope.
plan-challenger
Adversarial plan review agent — read-only. Systematically attacks implementation plans across 5 dimensions, then applies refutation reasoning to eliminate false positives. Never modifies code. Use before committing to any significant implementation plan.
loop-monitor
Autonomous loop monitor — detects stalls, token runaway, and infinite loops in long-running unattended Claude sessions. Use alongside a watchdog process when running autonomous pipelines.
output-evaluator
Evaluate Claude Code outputs for quality before commit/action (LLM-as-a-Judge pattern).
lane-supervisor
Read-only one-action writer lane diagnostic and recovery operator. Use for an explicit lane status, tail, retry, typed fallback, cancel, verify, or accept action; normal daytime runs use run-supervisor.