What is ccf-testing-and-qa?

Testing guidance for the Claude Code Framework, including what its automated checks verify and how to interpret their results.

Use it before declaring framework changes complete, when running or extending the test suite, or when a shell check fails and its purpose is unclear.

It prevents developers from treating a passing test run as proof of everything, or changing summary counts without updating the files those counts describe.

How BostonOrange/claude-code-framework configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to BostonOrange/claude-code-framework. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/BostonOrange/claude-code-framework/main/.claude/skills/ccf-testing-and-qa/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/BostonOrange/claude-code-framework

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/bostonorange/claude-code-framework/ccf-testing-and-qa/github.svg)](https://agentmods.dev/skills/bostonorange/claude-code-framework/ccf-testing-and-qa)

Your own site

<a href="https://agentmods.dev/skills/bostonorange/claude-code-framework/ccf-testing-and-qa"><img src="https://agentmods.dev/badge/skills/bostonorange/claude-code-framework/ccf-testing-and-qa/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/bostonorange/claude-code-framework/ccf-testing-and-qa"><img src="https://agentmods.dev/badge/skills/bostonorange/claude-code-framework/ccf-testing-and-qa.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 140 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,817 The whole file, excluding the scripts and references it only reads on demand.

Security scan D 2 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00140	$0.03817
Opus 5.5	$0.00056	$0.01527
Sonnet 5.5	$0.00028	$0.00763
Haiku 4.5	$0.00014	$0.00382

Measured 1mo ago against content hash 328f2dca43c8, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade D, and why

ccf-testing-and-qa scanned grade D 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 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

- **Templates/skills/setup scripts touched**: read the smoke section of the output — per-assert `[PASS]` lines, not just the table. Then `grep -r "{{" .claude/ CLAUDE.md | grep -v ".git"` in a scratch install (CLAUDE.md

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

3. **Hermeticity rules** — copy the proven patterns: `TMP_DIR=$(mktemp -d "${TMPDIR:-/tmp}/ccf-<name>.XXXXXX")` + `trap 'rm -rf "$TMP_DIR"' EXIT` (`tests/check-dogfood-drift.sh` lines 10–11), and per-case `HOME="$isolate

.claude/skills/ccf-testing-and-qa/SKILL.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CCF Testing and QA

The deterministic suite in tests/ is the hard gate for every framework change (CLAUDE.md "Self-Improvement" table). This skill covers what the suite proves, what it silently does not, how to extend it, and what evidence "done" requires. Maintainer's discipline rule: never hand-edit a count in isolation — counts change only together with the files they count, verified by tests.

Usage

Load when: running or interpreting tests/run-all.sh; deciding whether a green suite is sufficient evidence for a change; adding a new check-*.sh; debugging a red check.

Do NOT load for: which doc surface holds which count (that matrix is owned by ccf-doc-sync-campaign); bash↔PowerShell mirroring mechanics (ccf-parity-playbook); the meaning of allowlisted .claude/ drift (ccf-dogfood-and-drift); setup.sh internals when a smoke assert fails (ccf-release-and-install).

Process: verifying a change is "done"

Run the suite: bash tests/run-all.sh from repo root. It auto-discovers tests/check-*.sh by glob (find "$TESTS_DIR" -maxdepth 1 -name "check-*.sh", sorted). Consequence: tests/check-setup-smoke.ps1 is not discovered — the PowerShell smoke runs only in CI (.github/workflows/framework-tests.yml, powershell job on windows-latest). CI's bash job also runs bash -n setup.sh tests/*.sh templates/hooks/*.sh before the suite; run that locally too if you touched any shell file.
Read the real output, don't pattern-match the exit code. Expected shape as of 2026-07-11: 8 checks, a summary table, final line RESULT: ALL TESTS PASSED (8 of 8). Per-check Results lines today: agent-registry 234 passed, consistency 23, global-skill 6, guardrails 55, placeholders 47 (of 47 unique tokens), setup-smoke 80, templates 109; dogfood-drift prints Actual drift entries: N instead. A drop in these numbers under a green suite means coverage shrank — investigate.
Run the change-class checks (see "Evidence bar" below) — the suite does not cover everything.
If nothing gates your change class, extend the suite before merging (see "Adding a check").

Read the full file on GitHub · 103 lines

Changes

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 First seen · 103 lines · 140 tokens per session scan D 328f2dca43c8

Subscribe to this mod's changes

ccf-testing-and-qa is a skill published in the GitHub repository BostonOrange/claude-code-framework (3 stars, last pushed 3mo ago), licensed MIT. It adds 140 tokens to every session and 3,817 once invoked, about $0.0006 per session on Opus 5.5. A static security scan graded it D with 2 findings (reads agent configuration directories, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Testing

research-engineer

An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.

davila7/claude-code-templates · 43 tokens

tika-eval-compare

Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".

apache/tika · 50 tokens

cua-driver

Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.

davidondrej/skills · 68 tokens

claude-code-framework: Skill for Claude Code