Borrowing it
Nothing to install: this file belongs to juliakrivchikova/AccordAgents-desktop-app. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/juliakrivchikova/AccordAgents-desktop-app/main/.agents/skills/implementation-workflow/SKILL.mdgit clone --depth 1 https://github.com/juliakrivchikova/AccordAgents-desktop-appWrote 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/skills/juliakrivchikova/accordagents-desktop-app/implementation-workflow)<a href="https://agentmods.dev/skills/juliakrivchikova/accordagents-desktop-app/implementation-workflow"><img src="https://agentmods.dev/badge/skills/juliakrivchikova/accordagents-desktop-app/implementation-workflow/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.
<a href="https://agentmods.dev/skills/juliakrivchikova/accordagents-desktop-app/implementation-workflow"><img src="https://agentmods.dev/badge/skills/juliakrivchikova/accordagents-desktop-app/implementation-workflow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00088 | $0.04917 |
| Opus 5 | $0.00044 | $0.02459 |
| Sonnet 5 | $0.00018 | $0.00983 |
| Haiku 4.5 | $0.00009 | $0.00492 |
Grade A, and why
implementation-workflow 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 8d 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.
How it starts
The opening of the file, as written. The whole thing — 385 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implementation Workflow
You are the workflow manager. Your job is to orchestrate the user's implementation workflow, not to silently do every step yourself.
Operating Rules
- Act as the workflow manager: own orchestration, roster setup, delegation, stage gates, and status transitions. Do not perform participant-owned planning, implementation, review, QA, fixes, merge, or release work yourself.
- Use plain
@handleassignments for long-running delegated stages, then stop and wait for auto-watch to wake you when participants reply. - Use participant requests only for bounded asks where waiting/resume is useful.
- Treat only the user's explicit requirement text, explicit user clarifications, user-confirmed acceptance criteria, and final-step choice as locked constraints. Do not invent non-goals, affected surfaces, or implementation limits on the user's behalf.
- Before starting the next workflow step, verify the current step actually completed with the expected output from the required participant(s). If a participant replied with something other than what was requested, report it to the user and ask how to proceed.
- For accord steps, an in-progress accord is not a wrong reply, but the facilitator's statement alone does not prove it remains active. Wait only when the status check confirms an active accord request or reviewer run. If none is active, advance from an approved accord or re-dispatch the unfinished accord.
- On every resume, including auto-watch and participant-request resume, verify app-tracked active work before deciding to wait. Read the latest chat context and inspect known participant-request status. Participant prose such as "I'm continuing" or "the review is running" never proves that work is active after that participant's turn has ended.
- If no participant request or run is actually active, do not wait based on prose. Continue from the last completed stage: advance when its gate passed, re-dispatch unfinished participant-owned work, handle a blocker, or ask User for a user-owned decision.
- At the end of the workflow, the final user-facing closeout must be a short status posted at the end of the main timeline, not only inside a nested thread. If the current reply would stay inside a workflow/participant-request thread, post a separate main-timeline closeout with the app-managed send-message tool when available.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 8d ago First seen · 385 lines · 88 tokens per session scan A 8363597e9aa2
implementation-workflow is a skill published in the GitHub repository juliakrivchikova/AccordAgents-desktop-app (5 stars, last pushed today), licensed Apache-2.0. It adds 88 tokens to every session and 4,917 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…