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 skills/echoomegaprime/echo-qcoder/qcoder-coding-buildernpx skills add echoomegaprime/echo-qcoder --skill qcoder-coding-buildergit clone --depth 1 https://github.com/echoomegaprime/echo-qcoderWhat 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 | $0.00063 | $0.00537 |
| Opus 5 | $0.00032 | $0.00269 |
| Sonnet 5 | $0.00013 | $0.00107 |
| Haiku 4.5 | $0.00006 | $0.00054 |
Grade A, and why
qcoder-coding-builder 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 today.
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 — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
QCoder Coding Builder
Expected input
Require a concrete outcome and a workspace already placed in scope. Resolve ambiguity from the repository before asking. Never infer that a test, commit, deployment, or queue item succeeded.
Required sequence
- Read the root and nearest
AGENTS.mdplus any explicitly routedCLAUDE.mdor project overlay before editing. - Inspect
git status, the current branch, relevant manifests, tests, and nearby implementation. Preserve all unrelated changes. - Before new code, search ECHO Arcanum, the Code Library, and current official documentation through the scoped SOL SDK. Reuse an existing pattern when it fits.
- For nontrivial behavior, make the contract executable with a failing test, implement the smallest complete change, and rerun the focused test.
- Run proportional static, build, test, and security checks. Diagnose the actual failure mechanism before changing code after a failed gate.
- Commit only owned files with the ECHO repository identity when the active mission requires a commit. Register completed direct work and checkpoint material evidence.
Invoke moving ECHO facts through SYSTEMS/codex_auto/sol_cli.py sdk invoke; the launcher supplies SOL_RUN_ID, SOL_STATE_DB, and the scoped broker token. Never print or persist that token.
Decision points
- Stay in
cli-buildfor QCoder launcher and terminal integration work. - Switch the durable SOL mission when responsibility materially changes; include completed work, the next responsibility, and evidence in the checkpoint.
- Use an isolated verification copy when the primary checkout is too dirty to produce trustworthy release evidence.
- A passing unit test is not deployment proof. Use the repository's staging-first release gate when production behavior is in scope.
Facts that must not be inferred
Do not infer ownership of dirty files, successful installation, GPU residency, CI status, a pushed commit, or a live deployment. Read the relevant source of truth.
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.
- today First seen · 41 lines · 63 tokens per session scan A 8e3990976c94
qcoder-coding-builder is a skill published in the GitHub repository echoomegaprime/echo-qcoder (0 stars, last pushed yesterday), licensed MIT. It adds 63 tokens to every session and 537 once invoked, about $0.0003 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.
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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
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…