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 skills add amergrgic/kodama --skill kodama-verificationgit clone --depth 1 https://github.com/amergrgic/kodamaWrote 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/skills/amergrgic/kodama/kodama-verification)<a href="https://agentmods.dev/skills/amergrgic/kodama/kodama-verification"><img src="https://agentmods.dev/badge/skills/amergrgic/kodama/kodama-verification/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/skills/amergrgic/kodama/kodama-verification"><img src="https://agentmods.dev/badge/skills/amergrgic/kodama/kodama-verification.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 | $0.00031 | $0.00356 |
| Opus 5 | $0.00015 | $0.00178 |
| Sonnet 5 | $0.00006 | $0.00071 |
| Haiku 4.5 | $0.00003 | $0.00036 |
Grade A, and why
kodama-verification 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 10d 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
Verification Playbook
Define success before implementation
For non-trivial changes, record:
- Functional: what behavior must change or remain unchanged.
- Observable: what a test, command, or user flow must show.
- Pass/fail: binary conditions that demonstrate success.
Select the smallest meaningful evidence path from the repository's own tooling. Do not invent commands when project guidance already specifies them.
Implement and validate
- Read the affected code and tests.
- Add or update a targeted test when behavior changes.
- Run the targeted test first.
- Run the relevant lint, type check, build, or smoke test when available and proportionate to the change.
- For user-facing behavior, perform a manual verification when automation does not cover the flow.
Report evidence
Completion reports must state:
## Verification
- Command: `…`
- Result: exit code and meaningful summary
- Coverage: behavior or requirement verified
- Limitations: checks that could not run and why
Required evidence by change type
| Change | Minimum evidence |
|---|---|
| Bug fix | Reproduction or regression test plus fixed behavior. |
| New behavior | Targeted test plus relevant build/type/lint check. |
| Refactor | Existing targeted tests plus no behavior-change evidence. |
| Configuration | Validation command and expected output. |
| Documentation | Render, link, or example verification where applicable. |
Never say "should work", "tests pass", or "complete" without naming the evidence actually observed.
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.
- 10d ago First seen · 49 lines · 31 tokens per session scan A df555e29756e
kodama-verification is a skill published in the GitHub repository amergrgic/kodama (6 stars, last pushed yesterday), licensed MIT. It adds 31 tokens to every session and 356 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 2026-08-31.
Other skills, from other repositories
writing-tests
How to write a Kiro Crew backend test that has NO side effects and does not flake. Use when adding, editing, reviewing, or debugging a pytest test in the Kiro Crew source repo: which conftest is under your file, what leaks (temp dirs, the real data home, /.kiro, cron, threads, child processes), how to tell which of…
pod-e2e
ONLY for developing Kiro Crew itself -- if the project you are working on is anything else, ignore this skill: it drives Kiro Crew's own pod tooling, which does not exist in another repository. Boots a Kiro Crew feature worktree's full stack as an ISOLATED throwaway pod and proves it boots, authenticates and renders…
ai-discover
Parallel discovery of performance hotspots (perf track) and failure surfaces (bug track) for the auto-improvement loop. Fans out one subagent per hot-path area or failure surface; each returns ONE concrete, behavior-preserving fix candidate (perf) or a reproducing test plus fix (bug). Discovery only — no code changes…
auto/flaky-triage
Classify a red test as a real regression, a flake, or an environment problem before patching.
test-driven-development
TDD: enforce RED-GREEN-REFACTOR, tests before code.
unreal-engine
Build, debug, test, package, and optimize Unreal Engine projects using C++, Blueprints, Automation Tests, Unreal Build Tool, and Automation Tool. Use for .uproject work and Unreal-specific runtime or editor issues.