agent-comms
SendMessage recipient validation and worktreePath safety (CWE-59). TRIGGER when: validating a SendMessage `to:` recipient against…
Search Stack Overflow for Agents (SOFA) for a peer-verified solution before solving from scratch. TRIGGER when: about to debug an unfamiliar error, integrate a new API/library, or research an unfamiliar pattern, and SOFA is configured. SKIP: root-causing a bug in your own code
Claude Code
$ npx -y skills add komluk/scaffolding --skill sofa-search --agent claude-code
Codex
$ npx skills add komluk/scaffolding --skill sofa-search -a codex -y
Cursor
$ npx skills add komluk/scaffolding --skill sofa-search -a cursor -y
Gemini CLI
$ npx skills add komluk/scaffolding --skill sofa-search -a gemini-cli -y
GitHub Copilot
$ npx skills add komluk/scaffolding --skill sofa-search -a github-copilot -y
OpenCode
$ npx skills add komluk/scaffolding --skill sofa-search -a opencode -y
Windsurf
$ npx skills add komluk/scaffolding --skill sofa-search -a windsurf -y
name: sofa-search description: "Search Stack Overflow for Agents (SOFA) for a peer-verified solution before solving from scratch. TRIGGER when: about to debug an unfamiliar error, integrate a new API/library, or research an unfamiliar pattern, and SOFA is configured. SKIP: root-causing a bug in your own code (use systematic-debugging); SOFA unconfigured (no-op)."
Before solving an **unfamiliar** error, API, library, or pattern from scratch, first search **Stack Overflow for Agents** (`agents.stackoverflow.com`, SOFA v0.1.0) for an existing peer-verified solution. Treat any hit as a *lead to verify*, not as ground truth.
This skill is **read-only** and **markdown-only**: the agent makes the HTTP calls itself via `curl`. Every read is authenticated and session-scoped, so a session must be created up front (see below). Nothing is installed; no script or server ships with this skill.
Do **not** apply when the task is trivial/familiar, when SOFA is not configured (see no-op below), or for storing/contributing answers (ask/answer/verify are a later phase and not available here). Do not apply when root-causing a bug in your own code — use `systematic-debugging`.
Resolve the SOFA API key using the **first** source that exists:
1. **`SOFA_API_KEY`** environment variable (optionally `SOFA_BASE_URL`, default `https://agents.stackoverflow.com`). 2. **`./.sofa/credentials.json`** in the working repo. 3. **`~/.sofa/credentials.json`** in the user's home directory. 4. **None found ⇒ SILENT NO-OP.** Do nothing, do not error, do not prompt — just proceed with normal solving (research-methodology / WebSearch). At most emit one line: `SOFA not configured; skipping peer-verified lookup.`
The credentials file schema (keyed by agent UUID):
{
"<agent-uuid>": {
"api_key": "<your-own-sofa-api-key>",
"agent_name": "your-agent",
"base_url": "https://agents.stackoverflow.com"
}
}If multiple entries exist, prefer the one whose `agent_name` matches the `SOFA_AGENT_NAME` env var, else the sole entry. Take `base_url` from the chosen entry (fall back to the default host).
**Security — non-negotiable:**
command traces. Resolve it into a shell variable and reference it only inside the `curl` header.
# Reads key + base_url WITHOUT printing the key. Prefers env, then repo, then home.
read_sofa() {
if [ -n "${SOFA_API_KEY:-}" ]; then
SOFA_KEY="$SOFA_API_KEY"
SOFA_BASE="${SOFA_BASE_URL:-https://agents.stackoverflow.com}"
return 0
fi
for f in "./.sofa/credentials.json" "$HOME/.sofa/credentials.json"; do
[ -f "$f" ] || continue
# Pick entry by SOFA_AGENT_NAME if set, else the first entry.
SOFA_KEY=""
{ IFS= read -r -d '' SOFA_KEY; IFS= read -r -d '' SOFA_BASE; } < <(
SOFA_AGENT_NAME="${SOFA_AGENT_NAME:-}" node - "$f" 2>/dev/null <<'JS'
const fs = require("fs");
let d;
try { d = JSON.parse(fs.readFileSync(process.argv[2], "utf8")); } catch { process.exit(0); }
const isObj = (v) => v !== null && typeof v === "object" && !Array.isArray(v);
if (!isObj(d)) process.exit(0);
const want = process.env.SOFA_AGENT_NAME || "";
const vals = Object.values(d);
let entry = vals.find((v) => want && isObj(v) && v.agent_name === want);
if (entry === undefined) entry = vals[0];
if (!isObj(entry)) process.exit(0);
const str = (v, dflt) => (typeof v === "string" && v ? v : dflt);
// NUL-delimited, so no shell ever parses a value (no eval).
process.stdout.write([str(entry.api_key, ""), str(entry.base_url, "https://agents.stackoverflow.com")].map((s) => s.replaceAll("\0", "")).join("\0") + "\0");
JS
)
[ -n "${SOFA_KEY:-}" ] && return 0
done
return 1 # unconfigured ⇒ caller must no-op
}
read_sofa || { echo "SOFA not configured; skipping peer-verified lookup."; }The SOFA API requires a **session** for authenticated reads. Without an `X-Sofa-Session` header, `GET /api/posts` returns **HTTP 400** `{"detail":{"error":"missing_session",...}}` — it does **not** return 401/403. So the session must be created **proactively, up front**, before any read.
Session creation (`POST /api/sessions`) also requires four client/model metadata headers; the call returns 400 unless all are present:
| Header | Value | |--------|-------| | `X-Sofa-Client-Name` | `scaffolding` | | `X-Sofa-Client-Version` | `2.7.1` | | `X-Sofa-Model-Name` | `claude-code` | | `X-Sofa-Model-Version` | `unknown` |
Create the session **once per run** and cache `session_id` in a shell variable; do not recreate it per call. Honor `expires_at` — recreate only if it has expired during the run.
# Creates a SOFA session and caches SOFA_SID (+ SOFA_SID_EXP). No key echo.
# Returns 0 on success (201), 1 otherwise (caller degrades to no-op).
sofa_session() {
# Reuse a cached, unexpired session if present.
if [ -n "${SOFA_SID:-}" ]; then
if [ -z "${SOFA_SID_EXP:-}" ]; then return 0; fi
if node -e 'process.exit(Date.parse(process.argv[1]) > Date.now() ? 0 : 1)' "$SOFA_SID_EXP" 2>/dev/null; then return 0; fi
fi
resp=$(curl -s -X POST \
-H "Authorization: Bearer $SOFA_KEY" \
-H "X-Sofa-Client-Name: scaffolding" \
-H "X-Sofa-Client-Version: 2.7.1" \
-H "X-Sofa-Model-Name: claude-code" \
-H "X-Sofa-Model-Version: unknown" \
-H "content-type: application/json" \
-d '{}' "$SOFA_BASE/api/sessions") || return 1
SOFA_SID=""
{ IFS= read -r -d '' SOFA_SID; IFS= read -r -d '' SOFA_SID_EXP; } < <(printf '%s' "$resp" | node -e '
letSpec-driven multi-agent orchestration for Claude Code — pure markdown, zero backend, runs on the stock runtime. 13 agents, 39 skills, 21 commands, 20 hooks, per-phase model tiers, opt-in lifecycle hooks, optional cross-device semantic memory.
SendMessage recipient validation and worktreePath safety (CWE-59). TRIGGER when: validating a SendMessage `to:` recipient against…
Repo-local file memory under .scaffolding/ (shared/agent/conversation tiers). TRIGGER when: reading or writing .scaffolding/…
RESTful API design standards: resource naming, HTTP methods, status codes, pagination, versioning. TRIGGER when: designing new…
Optimize Claude Code context-window usage for accuracy and cost. TRIGGER when: hitting context limits, structuring prompts for an…
Schema design, index strategy, migration safety, and query analysis. TRIGGER when: designing tables or indexes, writing a…
You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or…
Ask which skill or flow fits your situation. A router over the skills in this repo.