procoder workflows.instructions.md

Project instructions for keeping continuous integration, or CI, reliable in the procoder project. CI is the automated system that checks a codebase after changes, while pins lock tools and actions to known versions.

In plain words
What is it for?
Maintaining procoder CI workflows, pinning tools and GitHub Actions, updating download and cache steps, and ensuring installed tools pass the project's doctor check.
Why use it?
They prevent the same code from receiving different checks because tools changed upstream. They also keep security checks, downloads, caches, and version verification aligned.

Instructions file for GitHub Copilot

Install

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.

agentmods
npx agentmods add instructions/azrtydxb/procoder/workflows
Clone the repo
git clone --depth 1 https://github.com/azrtydxb/procoder

Made for: GitHub Copilot.

Per session 412 This file is loaded in full into every session.
When invoked 412 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00412 $0.00412
Opus 5 $0.00206 $0.00206
Sonnet 5 $0.00082 $0.00082
Haiku 4.5 $0.00041 $0.00041

Measured yesterday against content hash b0e53e8ae56d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

procoder workflows.instructions.md 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 yesterday.

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.

.github/instructions/workflows.instructions.md · 45 lines

What it actually says

CI in procoder

Two tiers, kept apart on purpose: the gate answers about the change, CI answers about the tree. Do not move a whole-tree check into the gate to make a commit safer, and do not repeat the gate's answer in CI to make the pipeline look thorough.

Pins

Every tool whose answer the gate reports is pinned in .github/tool-versions.env, for the reason that file states in its own opening paragraph: the gate's verdict must not change because somebody upstream released something overnight.

Installing a tool from apt is not a pin. gitleaks was installed with apt-get install gitleaks, one line above a comment explaining that the versions are pinned, so CI ran 8.16.0 while a developer's machine ran 8.30.1 — and the two disagreed about whether the tree contained a secret. The gate gave two different verdicts for the same files.

A tool added to the download step must also be added to the loop that installs those binaries onto PATH, and to the cache key. procoder doctor runs afterwards and fails the job when one did not arrive, which is what that step is for.

Actions

Every action is pinned by commit SHA with its tag in a trailing comment. Every job carries timeout-minutes. Concurrency cancels in progress. procoder ci checks all three and will tell you which is missing.

Honesty in a job

A step that could not run must fail the job or say so in its output. "Nothing to do" and "did not run" are different results and CI is the last place that distinction survives — nobody reads a green pipeline's log.

Prefer a downloaded release binary over go install …@latest: compiling on every run cost 92 seconds for one tool, and @latest cannot be cached or pinned.

Changes

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.

  1. yesterday First seen · 45 lines · 412 tokens per session scan A b0e53e8ae56d

Subscribe to this mod's changes

procoder workflows.instructions.md is an instructions file published in the GitHub repository azrtydxb/procoder (196 stars, last pushed 2d ago), licensed Apache-2.0. It adds 412 tokens to every session, about $0.0021 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.

Related

Other instructions, from other repositories

sdlc-quality AGENTS.md

Instructions for zircote-plugins/sdlc-quality, covering agents.md - openai codex guidelines, project identity, quick context, agent guidelines and 1. understand the domain model.

zircote-plugins/sdlc-quality · 1,405 tokens

sdlc-quality copilot-instructions.md

Instructions for zircote-plugins/sdlc-quality, covering copilot instructions for sdlc plugin, project overview, repository structure, key conventions and rfc 2119 terminology.

zircote-plugins/sdlc-quality · 1,255 tokens

high-quality-projects-skill AGENTS.md

AGENTS.md instructions for RandyNorthrup/high-quality-projects-skill, covering agents.md, the two workflows, resolving paths, what is in here and non-negotiables when using this package.

RandyNorthrup/high-quality-projects-skill · 1,209 tokens

code-discipline-skills AGENTS.md

Instructions for eliranpv11/code-discipline-skills, covering code discipline, priority order, 1. think before coding, 2. verify reality before acting and 3. simplicity first.

eliranpv11/code-discipline-skills · 1,801 tokens

high-quality-projects-skill copilot-instructions.md

Copilot instructions for RandyNorthrup/high-quality-projects-skill: This repository provides two vendor-neutral workflows for holding a codebase to production standards.

RandyNorthrup/high-quality-projects-skill · 205 tokens

arbiterx CLAUDE.md

Instructions for NeelPrime/arbiterx, covering arbiterx engineering rules, setup, rules (always enforced), never generate and quality gate.

NeelPrime/arbiterx · 237 tokens