PR #2050 updated the root README.zh-CN.md install commands after the
everything-claude-code → ECC rename, but the same stale marketplace URL
remained in nine docs/<locale>/README.md copies. Align those quick-start
and self-hosted install blocks so /plugin install ecc@ecc resolves the
ecc marketplace instead of everything-claude-code.
The `/instinct-status` slash command template expanded
`${CLAUDE_PLUGIN_ROOT}` directly and documented a manual-install
fallback to `~/.claude/skills/continuous-learning-v2/scripts/instinct-cli.py`.
When users had both an active plugin install (under
`~/.claude/plugins/cache/<slug>/<org>/<version>/`) and a legacy
`~/.claude/skills/continuous-learning-v2/` directory left over from a
previous manual install, an empty `CLAUDE_PLUGIN_ROOT` (which Claude
Code does not always populate in slash-command shell contexts) silently
made the command read the stale legacy install while the active plugin
hooks and observer wrote to the new XDG path. The user saw "No
instincts found" while the system was actively learning — exactly the
divergence the bug reporter spent hours diagnosing.
Replace the brittle two-block template with the same inline resolver
pattern that `hooks/hooks.json` and `/sessions` / `/skill-health`
already use: env var → standard install → known plugin roots → plugin
cache walk → fallback. The resolver is the canonical `INLINE_RESOLVE`
constant from `scripts/lib/resolve-ecc-root.js`, so no new code is
introduced — just consistent adoption of the existing pattern.
Apply the same fix to all five copies of the command:
- commands/instinct-status.md (canonical)
- .opencode/commands/instinct-status.md
- docs/zh-CN/commands/instinct-status.md
- docs/ja-JP/commands/instinct-status.md
- docs/tr/commands/instinct-status.md
Extend tests/lib/command-plugin-root.test.js with an assertion that the
canonical instinct-status.md uses the inline resolver and no longer
hard-codes the legacy `~/.claude/skills/...` fallback (regression
guard).
zh-CN copy: polish the Chinese phrasing per LanguageTool feedback
(`使用与 ... 相同的解析器` → `以与 ... 相同的解析器`) so the verb is
introduced by an explicit preposition instead of reading as an awkward
verb-object construction.
After the XDG migration the CLI reads from
$XDG_DATA_HOME/ecc-homunculus/ (default ~/.local/share/ecc-homunculus/),
but installs that retained an older manual copy at ~/.claude/homunculus/
saw observations land in the new location while `instinct-cli.py status`
silently continued to look at the new directory only. The reporter
spent hours tracing the divergence because nothing surfaced the legacy
tree.
Add `_detect_legacy_homunculus_dir()` which returns the legacy path
when ~/.claude/homunculus/ contains real ECC state (projects/,
instincts/, evolved/, or observations.jsonl) and the active
HOMUNCULUS_DIR is different. `cmd_status` calls it at the bottom of
its output and prints a one-time, scoped warning that names both
paths and points at the existing migrate-homunculus.sh script.
Empty placeholder directories (just ~/.claude/homunculus/ with no
content) are ignored so users who have already migrated and left the
empty shell behind don't get nagged on every status call.
Tests cover three branches: populated legacy dir triggers the warning,
absent legacy dir stays silent, and empty placeholder legacy dir stays
silent.
The observer's MAX_TURNS default of 20 was systematically insufficient
for the MAX_ANALYSIS_LINES default of 500. First-cycle analysis on a
fresh project consistently failed with "Reached max turns (20)", forcing
users to either raise ECC_OBSERVER_MAX_TURNS or lower
ECC_OBSERVER_MAX_ANALYSIS_LINES before the observer became useful.
Pair the defaults so the out-of-the-box experience succeeds: bump
MAX_TURNS to 50 (the value the reporter empirically settled on for the
500-line default). The safety floor (turns < 4 falls back to default) is
preserved.
Test asserting the default constant is updated alongside the source.
Review follow-up (CodeRabbit + cubic): switching to safeParseJson at line
389 means packageJson can be null on a missing/malformed package.json, but
the quality-ci-validations check dereferenced packageJson.scripts before the
optional chaining could help — throwing TypeError instead of degrading.
Guard the base object with packageJson?.scripts?.test at the access site,
matching the file's existing convention (e.g. line 220 uses packageJson?.name).
Generated with [Claude Code](https://claude.ai/code)
via [Happy](https://happy.engineering)
Co-Authored-By: Claude <noreply@anthropic.com>
Co-Authored-By: Happy <yesreply@happy.engineering>
- scripts/harness-audit.js: getRepoChecks() parsed package.json with raw
JSON.parse(readText(...)), while the rest of the file (lines 218, 822)
uses the tolerant safeParseJson(safeRead(...)). In repo target mode a
project lacking package.json — or with malformed JSON — threw an uncaught
exception and crashed the audit instead of degrading. Match the existing
convention so the audit tolerates a missing/invalid package.json.
- skills/frontend-slides/scripts/export-pdf.sh: `set -- "${POSITIONAL[@]}"`
expands an empty array under `set -u` on bash 3.2 (the macOS system bash),
aborting with "POSITIONAL[@]: unbound variable" instead of printing the
usage message when invoked with no positional args. Guard the expansion
with ${POSITIONAL[@]+"${POSITIONAL[@]}"} (no-op safe under bash 3.2 set -u).
Generated with [Claude Code](https://claude.ai/code)
via [Happy](https://happy.engineering)
Co-Authored-By: Claude <noreply@anthropic.com>
Co-Authored-By: Happy <yesreply@happy.engineering>
Removed skills/evalview-agent-testing/ which required `pip install evalview`
from an unvetted third-party package. ECC skills must be self-contained
and not require installing external packages to function.
If we need agent regression testing, we build it natively in ECC.
Adds integration skill for ORCH (@oxgeneral/orch) — a TypeScript CLI runtime
that coordinates Claude Code, OpenCode, Codex, and Cursor agents as a typed
engineering team with formal state machine, auto-retry, and inter-agent messaging.
Use this skill when ECC tasks need to survive multiple sessions, require a review
gate before completion, or involve a persistent specialized agent team.
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
Co-authored-by: Affaan Mustafa <me@affaanmustafa.com>
* feat(skills): add evalview-agent-testing skill and MCP server
Add EvalView as a regression testing skill for AI agents. EvalView
snapshots agent behavior (tool calls, parameters, output), then diffs
against baselines after every change — catching regressions before they
ship.
Skill covers:
- CLI workflow (init → snapshot → check → monitor)
- Python API (gate() / gate_async() for autonomous loops)
- Quick mode (no LLM judge, $0, sub-second)
- CI/CD integration (GitHub Actions with PR comments)
- MCP integration (8 tools for Claude Code)
- Multi-turn test cases
- OpenClaw integration for autonomous agents
Also adds evalview MCP server to mcp-servers.json.
* fix(skills): pin action SHA and remove unvetted external links
- Pin hidai25/eval-view action to commit SHA instead of @main
- Replace external GitHub links with PyPI package link (vetted registry)
Addresses cubic-dev-ai review feedback.
* fix(skills): replace third-party action with pip install + CLI
Use plain pip install + evalview CLI instead of a third-party GitHub
Action. No external actions, no secrets passed to unvetted code.
Addresses cubic-dev-ai supply-chain review feedback.
* fix(skills): add destructive revert warning for gate_or_revert
Add prominent warning that gate_or_revert runs git checkout,
discarding uncommitted changes. Documents the revert_cmd override
for safer alternatives like git stash.
Addresses cubic-dev-ai review feedback.
* fix(skills): pin pip version range and document fail-on tradeoffs
- Pin evalview to >=0.5,<1 to prevent breaking CI on major upgrades
- Document --fail-on REGRESSION vs --strict tradeoff so users
understand what gates and what passes through
Addresses greptile-apps review feedback.
* fix: use python3 -m evalview for venv compatibility in MCP config
Follows the same pattern as insaits entry. Resolves correctly even
when evalview is installed in a virtual environment that isn't on
the system PATH.
* fix: align MCP install command with mcp-servers.json pattern
Use python3 -m evalview mcp serve consistently across both the
skill docs and the MCP config catalog.
* fix: use evalview CLI entry point for MCP command
pip install evalview installs the evalview binary to PATH, so using
it directly is consistent with the install docs and avoids python3
version mismatch issues.
* fix: pin install version to match CI section
* fix: pin all pip install references consistently
* fix: add API key placeholder and pin install version in MCP config
Add OPENAI_API_KEY env placeholder matching other entries. Note that
the key is optional — deterministic checks work without it. Pin
install version to match skill docs.
* fix: guard score_delta format for non-scored statuses
---------
Co-authored-by: Affaan Mustafa <me@affaanmustafa.com>
