404 · route not found
+This address is not part of the current TestForge site. Recover through a maintained customer route instead of trusting a stale or repository-relative link.
+ +Free Collaborative Dynamics Augment · two matched SKILLs · deterministic tools · independent review · behavioral eval testbed
+
Begin successfully
+TestForge is for developers, release owners, coding-Agent operators, and Augment builders who need evidence stronger than “the tests are green.” It is not a product-design workshop, penetration-testing authorization, compliance certification, or proof that defects do not exist.
+A bounded target and revision; the intended behavior or requirement; relevant diff, source, tests, logs, and environment facts; plus explicit authority for any consequential action.
An impact map, ranked risks, invariants, scenarios, tests or commands, captured execution evidence, classified findings, residual risks, reviewer disposition, and exactly one bounded release status.
The operator distinguishes observed, inferred, assumed, unresolved, executed, and authorized claims; links critical risks to credible evidence; and refuses confidence that the evidence cannot support.
$software-verification Verify this completed candidate at revision <REVISION>. The intended behavior is <REQUIREMENT>. Inspect the available source and tests, run only safe authorized checks, and issue an evidence-backed release assessment.$verification-reviewer Independently challenge the resulting verification package. Find the smallest consequential break in its evidence chain and judge whether the proposed status is supportable.The practical wager
@@ -195,29 +213,41 @@Install or inspect
-Install, verify, maintain
+codex plugin marketplace add Stunspot/TestForge
codex plugin add testforge@cd-testforge
- Installs the two aligned self-contained verification skills.
+Start a new task. Invoke $software-verification, then use a second fresh task to invoke $verification-reviewer. Verify that each can reach its package-relative resources.
Copy both complete folders under testforge/skills/ into the personal Codex skills directory. Keep every reference, template, example, fallback, and script with its owning skill.
On Windows, the final paths normally end in .codex\skills\<skill-name>\SKILL.md. Restart and probe both handles separately.
Download the release, keep the `testforge/` tree together, and expose both directories under `testforge/skills/` through the host’s skill mechanism.
+ CLAUDE +Confirm the account exposes custom Skills. Upload claude-ai/software-verification-v1.1.6.zip and claude-ai/verification-reviewer-v1.1.6.zip separately, enable both when required, and test each in a new conversation.
Live upload, discovery, resource loading, script execution, and reviewer handoff were not exercised for this release.
py -m pip install -r tools\augment-evals\requirements.txt
- py tools\augment-evals\augment_eval.py validate testforge
- Raw runs remain local; reviewed compact baselines may be promoted into Git-tracked records.
+ OTHER HOSTS +A host must load Markdown skill instructions and preserve package-relative resources. Otherwise use the fileless fallback. Deterministic tools require Python 3.10+; unsupported stacks degrade to generic scenario and command planning.
+Record the installed version and preserve required evidence. Replace both skills from the same release, start a fresh task or conversation, and repeat both discovery and resource probes. Never mix operator and reviewer versions.
+Remove or disable the plugin and both skills through the host manager, or delete only the two exact standalone folders. TestForge has no account, daemon, telemetry store, or product database. Local manifests, reports, tests, raw captures, baselines, and eval runs remain ordinary files until you archive or delete them under project policy.
Detailed routes: Codex lifecycle · Claude lifecycle · host boundary.
Start from the change
@@ -229,6 +259,61 @@Troubleshoot and recover
+Start a fresh task, verify the plugin state or final folder path, confirm the complete folder—not a lone SKILL.md—is installed, and check host or organization enablement.
Invoke the handle explicitly, state the target and release claim, and verify package-relative doctrine is reachable. Do not treat a plausible answer as proof the skill loaded.
Record the command, working directory, exit code, exact error, and unavailable guarantee. Classify product, test, environment, or tooling cause before changing anything.
Stop the cycle, retain raw evidence, and use the reviewer in a fresh context. A product defect returns the candidate upstream; it is not repaired inside that TestForge cycle.
Privacy, storage, network, security
+The v1.1.6 skills-only plugin includes no account, telemetry, analytics, hosted service, connector, MCP server, hook, or automatic network request. Deterministic scripts touch only paths and commands the user chooses.
Prompts, repositories, logs, uploads, model calls, retention, training, residency, and connector traffic are governed by Codex, Claude, configured models, Git hosts, and any authorized tools—not by TestForge.
Verification manifests, reports, raw command captures, generated tests, evaluation runs, seals, and promoted baselines may contain sensitive project evidence. Store and delete them under an approved retention policy.
Imported files and tool output are untrusted evidence. Active security work needs a named target, explicit permission, non-production default, time window, rate limits, prohibited actions, handling rules, and a stop contact.
Provenance and evidence status
+| Claim | Current evidence | Boundary |
|---|---|---|
| Constructed and packaged | v1.1.6 source, plugin tree, current Claude archives, manifests, and retained frozen-release receipts | Does not prove host installation or live behavior |
| Deterministic behavior | Repository-local tool, package, distribution, documentation, and eval-harness suites | Only exercised commands, fixtures, Python version, and environment |
| Behavioral evaluation | Named model/context baselines and a deliberately failed fresh-package smoke | Single-trial, model-, context-, case-, and judge-bounded; not universal model quality |
| OpenAI directory | Latest retained portal packet is v1.1.4 and repository-tested | No claim of upload, approval, publication, or discoverability |
| Host activation | Installation probes are documented | Current live Codex and Claude activation remain separate observations |
Trust and authority
@@ -245,7 +330,7 @@