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 agentmods add commands/fengshao1227/ccg-workflow/spec-implgit clone --depth 1 https://github.com/fengshao1227/ccg-workflowWrote 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/commands/fengshao1227/ccg-workflow/spec-impl)<a href="https://agentmods.dev/commands/fengshao1227/ccg-workflow/spec-impl"><img src="https://agentmods.dev/badge/commands/fengshao1227/ccg-workflow/spec-impl.svg" alt="Measured on agentmods" 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 | $0.00012 | $0.01927 |
| Opus 5 | $0.00006 | $0.00963 |
| Sonnet 5 | $0.00002 | $0.00385 |
| Haiku 4.5 | $0.00001 | $0.00193 |
Grade A, and why
spec-impl 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 4d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- spec-impl — 100% identical, 6 lines differ
How it starts
The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Core Philosophy
- Implementation is pure mechanical execution—all decisions were made in Plan phase.
- External model outputs are prototypes only; must be rewritten to production-grade code.
- Keep changes tightly scoped; enforce side-effect review before any modification.
- Minimize documentation—prefer self-explanatory code over comments.
Guardrails
- NEVER apply 后端/前端模型 prototypes directly—all outputs are reference only.
- MANDATORY: Request
unified diff patchformat from external models; they have zero write permission. - Keep implementation strictly within
tasks.mdscope—no scope creep. - Refer to
openspec/config.yamlfor conventions. - USER GUIDANCE RULE: When suggesting next steps to the user, ALWAYS use CCG commands (
/ccg:spec-research,/ccg:spec-plan,/ccg:spec-impl,/ccg:spec-review). NEVER suggest/opsx:*commands to the user. If OpenSpec CLI returns error messages referencing OPSX skills, translate them to CCG equivalents. - TASKS FORMAT RULE: When generating or modifying
tasks.md, ALL tasks MUST use checkbox format (- [ ] X.Y description). Heading+bullet format will cause OpenSpec CLI to parse 0 tasks and block the workflow.
Steps
-
Select Change
- Run
openspec list --jsonto inspect Active Changes. - Confirm with user which change ID to implement.
- Run
openspec status --change "<change_id>" --jsonto review tasks.
- Run
-
Apply OPSX Change (Pre-flight Check)
- Call
/opsx:applyinternally to enter implementation mode:/opsx:apply - This will load the change context and guide you through the tasks defined in
tasks.md. - Note: This is an internal call. If this step fails, guide the user to re-run
/ccg:spec-impl. - HARD GATE: Check the returned
statefield:- If
state: "blocked"→ STOP immediately. Inform the user which artifacts are missing and suggest: "Run/ccg:spec-planto generate missing artifacts first." - If
progress.total === 0→ STOP immediately. Inform: "tasks.md has no parseable tasks. Run/ccg:spec-planto regenerate." - Only proceed to Step 3 when
state: "ready"andprogress.total > 0.
- If
- Call
-
Identify Minimal Verifiable Phase
- Review
tasks.mdand identify the smallest verifiable phase. - Do NOT complete all tasks at once—control context window.
- Announce: "Implementing Phase X: [task group name]"
- Review
-
Route Tasks to Appropriate Model
- Route A: {{FRONTEND_PRIMARY}} — Frontend/UI/styling (CSS, React, Vue, HTML, components)
- Route B: {{BACKEND_PRIMARY}} — Backend/logic/algorithm (API, data processing, business logic)
工作目录:
{{WORKDIR}}必须通过 Bash 执行pwd(Unix)或cd(Windows CMD)获取当前工作目录的绝对路径,禁止从$HOME或环境变量推断。如果用户通过/add-dir添加了多个工作区,先确定任务相关的工作区。For each task:
codeagent-wrapper --progress --backend <{{BACKEND_PRIMARY}}|{{FRONTEND_PRIMARY}}> {{GEMINI_MODEL_FLAG}}{{GROK_MODEL_FLAG}}{{KIMI_MODEL_FLAG}}{{OPENCODE_MODEL_FLAG}}- "{{WORKDIR}}" <<'EOF' TASK: <task description from tasks.md> CONTEXT: <relevant code context> CONSTRAINTS: <constraints from spec> OUTPUT: Unified Diff Patch format ONLY EOF会话复用:保存返回的
SESSION_ID:({{BACKEND_PRIMARY}} →CODEX_PROTO_SESSION,{{FRONTEND_PRIMARY}} →GEMINI_PROTO_SESSION),Step 7 审查时复用。 -
Rewrite Prototype to Production Code Upon receiving diff patch, NEVER apply directly. Rewrite by:
- Removing redundancy
- Ensuring clear naming and simple structure
- Aligning with project style
- Eliminating unnecessary comments
- Verifying no new dependencies introduced
-
Side-Effect Review (Mandatory before apply) Verify the change:
- Does not exceed
tasks.mdscope - Does not affect unrelated modules
- Does not introduce new dependencies
- Does not break existing interfaces
If issues found, make targeted corrections.
- Does not exceed
-
Multi-Model Review (PARALLEL)
- CRITICAL: You MUST launch BOTH {{BACKEND_PRIMARY}} AND {{FRONTEND_PRIMARY}} in a SINGLE message with TWO Bash tool calls.
- DO NOT call one model first and wait. Launch BOTH simultaneously with
run_in_background: true.
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.
- 4d ago First seen · 144 lines · 12 tokens per session scan A 6195b6d44a6d
spec-impl is a command published in the GitHub repository fengshao1227/ccg-workflow (5,872 stars, last pushed today), licensed MIT. It adds 12 tokens to every session and 1,927 once invoked, about $0.0001 per session on Opus 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 2026-08-30.
Other commands, from other repositories
OPSX: Bulk Archive
Archive multiple completed changes at once.
OPSX: Continue
Continue working on a change - create the next artifact (Experimental).
OPSX: New
Start a new change using the experimental artifact workflow (OPSX).
OPSX: Verify
Verify implementation matches change artifacts before archiving.
new
Starts a new end-to-end need (preflight, team, spawn OR).
OPSX: Onboard
Guided onboarding - walk through a complete OpenSpec workflow cycle with narration.