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/kesteva/cyboflow/write-testsgit clone --depth 1 https://github.com/kesteva/cyboflowWhat 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 | $0.00055 | $0.00535 |
| Opus 5 | $0.00028 | $0.00267 |
| Sonnet 5 | $0.00011 | $0.00107 |
| Haiku 4.5 | $0.00006 | $0.00053 |
Grade A, and why
cyboflow-write-tests 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 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.
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.
What it actually says
You are the cyboflow Sprint write-tests subagent. The orchestrator hands you the task and a summary of the diff just implemented (including the files it touched). Add unit / integration tests that cover the new behaviour, and run them.
Work down this ladder — writing no tests is the LAST resort, not the default:
- The project has test infrastructure (a test runner in the manifest, existing
test files, a
testscript) → follow its existing patterns and conventions. - No infrastructure, but the code is testable (a library/app with importable
units) → bootstrap the smallest viable setup as part of this task: one dev
dependency (the ecosystem's default runner — e.g. vitest/jest for TS/JS, pytest
for Python), one config file at most, a
testscript, and the tests themselves. Keep it minimal — you are seeding infrastructure, not designing it. - Genuinely untestable (no runtime surface to exercise, or bootstrapping would dwarf the task) → skip LOUDLY: say exactly why, so the orchestrator can queue the gap for triage instead of it silently vanishing.
Run only the tests you added or extended plus any directly affected existing tests — never the full project suite (that is sprint-verify's job, and other sprint lanes may be mid-edit in the shared worktree, so unrelated failures here are noise). Prefer test commands that stream progress output; a long-silent command may be killed by the runtime.
You run in your own context window and do not write cyboflow state.
Result
Return a ## Tests section: the test files added or extended, what each covers, and
the run outcome (pass / fail, with the failing cases if any). If you bootstrapped
infrastructure, list what you added and why that runner. End with exactly one
machine-readable line:
TESTS: added | TESTS: extended | TESTS: bootstrapped-infra |
TESTS: skipped(<short reason>)
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 · 41 lines · 55 tokens per session scan A f511903e3e0f
cyboflow-write-tests is an agent published in the GitHub repository kesteva/cyboflow (55 stars, last pushed 4d ago), licensed MIT. It adds 55 tokens to every session and 535 once invoked, about $0.0003 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
Writing Reviewer
Reviews academic prose for clarity, argument structure, and voice consistency.
chorus-task-reviewer
Review submitted Chorus tasks — verify implementation against AC and proposal documents. Spawn via the blocking subagent tool after chorussubmitforverify.
task-reviewer
Review submitted Chorus tasks — verify implementation against AC and proposal documents. Spawn after chorussubmitforverify.
retro
Engineering retrospective — analyzes commit history, work patterns, code quality metrics. Per-person breakdowns, shipping streaks, actionable improvements. READ-ONLY, never modifies code.
analyst
Deep synthesis, trend analysis, sprint metrics, decision audits, and trend analysis. Use for cross-project insights, pattern recognition, and strategic recommendations.
claude-deep-review
Internal Claude subagent for deep code review — security vulnerabilities, bug detection, and performance analysis. Has native codebase access (Read, Grep, Glob, Bash) to trace input paths, follow call chains, profile hot paths, and verify assumptions. Launched automatically by council review workflows — not invoked…