plan-forge status-reporting.instructions.md

A set of templates for reporting progress, completed work, blockers, handoffs, and failures during Plan Forge runs. Plan Forge is a system that coordinates development plans and multiple coding agents.

In plain words
What is it for?
Use the templates during plan execution, autonomous runs, slice monitoring, and session handoffs.
Why use it?
It makes long-running or multi-agent work easier to follow by keeping status updates consistent and showing what is done, blocked, and next.

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/srnichols/plan-forge/status-reporting
Clone the repo
git clone --depth 1 https://github.com/srnichols/plan-forge

Made for: GitHub Copilot.

Per session 1,373 This file is loaded in full into every session.
When invoked 1,373 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 $0.01373 $0.01373
Opus 5 $0.00687 $0.00687
Sonnet 5 $0.00275 $0.00275
Haiku 4.5 $0.00137 $0.00137

Measured 2d ago against content hash 8c64c23d746e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

plan-forge status-reporting.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 2d 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.

.github/instructions/status-reporting.instructions.md · 178 lines

How it starts

The opening of the file, as written. The whole thing — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Status Reporting Templates

When to use: During forge_run_plan execution, multi-agent orchestration, autonomous runs, slice monitoring, and session handoffs. Use the template that matches the moment — don't force every message into a template.


Template 1: Progress Update

Use during long-running operations to report current state. Send every 2–3 slices or every 5 minutes, whichever comes first.

## Progress Update

**Run:** <plan name>
**Current:** Slice <N> — <slice title>
**Status:** <Running | Waiting for gate | Queued>
**Completed:** <N>/<total> slices passed
**Failed:** <N> (if any)
**Next:** Slice <N+1> — <title>
**ETA:** ~<X> minutes remaining

Example:

## Progress Update

**Run:** Phase-22-COPILOT-PLATFORM-v2.15
**Current:** Slice 3 — `forge_export_plan`
**Status:** Running (~10 min so far)
**Completed:** 2/8 slices passed
**Failed:** 0
**Next:** Slice 4 — `forge_sync_memories`
**ETA:** ~35 minutes remaining

Template 2: Slice Complete

Use immediately after a slice passes its validation gate.

## Slice Complete

**Slice:** <N> — <title>
**Result:** <Passed | Passed with warnings>
**Duration:** <X> min
**Gate:** <gate evidence summary>
**Files changed:** <count>
**Key outputs:** <1–2 line summary of what was built>
**Next:** Slice <N+1> — <title>

Template 3: Blocker Report

Use when execution is stalled and needs human input or a fix.

## ⚠ Blocker

**Slice:** <N> — <title>
**Problem:** <what failed>
**Cause:** <root cause or best guess>
**Impact:** <what's blocked downstream>
**Attempted:** <what was tried, if anything>
**Next action:** <specific fix or question for human>

Template 4: Failure / Recovery Report

Use when a slice fails its gate and the system is retrying or escalating.

## ❌ Slice Failed

**Slice:** <N> — <title>
**Attempt:** <N> of <max>
**Error:** <error message or gate output>
**Model:** <model used>
**Recovery:** <Retrying | Escalating to <model> | Awaiting human input>
**Files affected:** <list>

Read the full file on GitHub · 178 lines

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. 2d ago First seen · 178 lines · 1,373 tokens per session scan A 8c64c23d746e

Subscribe to this mod's changes

plan-forge status-reporting.instructions.md is an instructions file published in the GitHub repository srnichols/plan-forge (5 stars, last pushed 22d ago), licensed MIT. It adds 1,373 tokens to every session, about $0.0069 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.

Related

Other instructions, from other repositories

dotnet-skills AGENTS.md

Instructions for managedcode/dotnet-skills, covering agents.md, purpose, solution topology, rule precedence and path and linking rules.

managedcode/dotnet-skills · 13,592 tokens

dotnet-skills copilot-instructions.md

Instructions for managedcode/dotnet-skills: Use AGENTS.md as the repository-wide source of truth for workflow, catalog structure, release policy, and skill maintenance rules.

managedcode/dotnet-skills · 97 tokens

Perigon.CLI copilot-instructions.md

Instructions for AterDev/Perigon.CLI, covering github copilot instructions, general guidelines, 技术栈, 项目结构与分层 and 代码风格约定.

AterDev/Perigon.CLI · 1,254 tokens

copilot-instructions copilot-instructions.md

Instructions for SebastienDegodez/copilot-instructions, covering copilot instructions, language policy, development code generation and workflow implementation.

SebastienDegodez/copilot-instructions · 364 tokens

maf-doctor maf-deployment.instructions.md

Always-loaded production-deployment patterns for MAF 1.3.0. Auto-applies to Program.cs, DI registration files, and infra config. Covers ManagedIdentityCredential, MaxTokens caps, secret handling, OpenTelemetry wiring, and the analyzer rules that catch regressions at write time.

joslat/maf-doctor · 1,884 tokens

maf-doctor copilot-instructions.md

Instructions for joslat/maf-doctor, covering maf 1.3.0 migration — auto-loaded constraints, maf 1.3.0 — constraints & breaking changes reference, hard constraints (never violate), fan-out / fan-in rules (silent failure risk) and key breaking changes.

joslat/maf-doctor · 1,604 tokens