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 dinhanhthi/coding-friend --skill cf-verificationgit clone --depth 1 https://github.com/dinhanhthi/coding-friendWrote 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/dinhanhthi/coding-friend/cf-verification)<a href="https://agentmods.dev/skills/dinhanhthi/coding-friend/cf-verification"><img src="https://agentmods.dev/badge/skills/dinhanhthi/coding-friend/cf-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/dinhanhthi/coding-friend/cf-verification"><img src="https://agentmods.dev/badge/skills/dinhanhthi/coding-friend/cf-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 | $0.00122 | $0.00668 |
| Opus 5.5 | $0.00049 | $0.00267 |
| Sonnet 5.5 | $0.00024 | $0.00134 |
| Haiku 4.5 | $0.00012 | $0.00067 |
Grade A, and why
cf-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 1mo 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verification Before Completion
Custom Guide
bash "<plugin-root>/lib/load-custom-guide.sh" cf-verification
If the block above printed anything, apply only the ## Before, ## Rules, and ## After sections; if it shows the raw command instead of output, re-run that exact load-custom-guide.sh fence now.
The Gate
No completion claims without fresh verification evidence.
Claiming work is complete without verification is dishonesty, not efficiency.
When to Auto-Invoke
Auto-invoke this skill after tasks that produce or modify code (implementation, bug fixes, refactoring).
Do NOT auto-invoke after analysis-only skills that don't change code:
/cf-review— code review is analysis, not implementation/cf-plan— planning doesn't produce code/cf-ask— Q&A doesn't produce code/cf-research— research doesn't produce code
Checklist
Before claiming ANY task is done:
- Run tests — Execute the test suite. Read the output. All tests must pass.
- Run the build — If applicable, build the project. No errors.
- Lint/format — If configured, run linter. No new warnings.
- Manual check — For UI changes, verify visually. For API changes, test the endpoint.
- Show evidence — Include test output, build output, or screenshots in your response.
- Slop check — Scan changed code for AI transmarks, excessive comments, unnecessary verbosity.
What Counts as Evidence
| Good Evidence | Bad Evidence |
|---|---|
| Test output showing all pass | "I believe the tests pass" |
| Build output with exit code 0 | "The build should work" |
| Actual command output | "I ran the tests" (without output) |
| Screenshot of UI change | "The UI looks correct" |
git diff showing the change |
"I made the change" |
Common Failures
- Tests pass
- No type errors (TypeScript/typed languages)
- Linter clean
- Build succeeds
- No console errors/warnings
- Feature works as described
- No regressions in existing functionality
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.
- 1mo ago Changed · +3 lines · +112 tokens per session b4dd8d556421
- 2mo ago First seen · 70 lines · 10 tokens per session scan A fcb2fd531c7e
cf-verification is a skill published in the GitHub repository dinhanhthi/coding-friend (4 stars, last pushed today), licensed MIT. It adds 122 tokens to every session and 668 once invoked, about $0.0005 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 2026-08-31.
cf-verification compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| cf-verificationdinhanhthi/coding-friend | Skill | 4 | today | MIT | A | 122 | Claude Code |
| develop-with-evidenceapache/doris-skills | Skill | 49 | 2d ago | Apache-2.0 | A | 147 | Codex |
| officecli-pitch-deckiOfficeAI/OfficeCLI | Skill | 33k | 7d ago | Apache-2.0 | A | 163 | Claude Code, Codex |
| morph-pptiOfficeAI/OfficeCLI | Skill | 33k | 7d ago | Apache-2.0 | A | 169 | Claude Code, Codex |
| officecli-academic-paperiOfficeAI/OfficeCLI | Skill | 33k | 7d ago | Apache-2.0 | A | 141 | Claude Code, Codex |
| officecli-financial-modeliOfficeAI/OfficeCLI | Skill | 33k | 7d ago | Apache-2.0 | A | 222 | Claude Code, Codex |
| officecli-pptxiOfficeAI/OfficeCLI | Skill | 33k | 7d ago | Apache-2.0 | A | 106 | Claude Code, Codex |