task-amend

A command for changing a task's objective, acceptance rules, file scope, or verification definition while work is underway. It records the proposed changes and the reason for them.

In plain words
What is it for?
Use it after settling a change to a task's goals, allowed files, context, acceptance criteria, or verification command.
Why use it?
It keeps the task contract accurate when the agreed work changes, instead of leaving workers and reviewers with outdated instructions.

Command

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 commands/thixpin/pitway/task-amend
Clone the repo
git clone --depth 1 https://github.com/thixpin/pitway
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 206 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00014 $0.00206
Opus 5 $0.00007 $0.00103
Sonnet 5 $0.00003 $0.00041
Haiku 4.5 $0.00001 $0.00021

Measured 2d ago against content hash c2cac5abc292, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

task-amend 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.

src/integrations/claude/commands/task-amend.md · 25 lines

What it actually says

task-amend

Role: Main Agent

pitway task-amend <task-id> --file <path> --change-log <text> [--json]

Use when a task's own definition needs to change mid-flight — its objective, acceptance criteria, file scoping (relevant_files / context_files / write_scope), or verification — without that rising to the level of a full contract amendment. Requires --file (the proposed field changes) and --change-log (why); running the command is itself the approval, so only run it once the change is actually settled, not while still exploring options with the developer.

Amendment object format: ../draft-formats.md.

See ../protocol-driver.md. Run pitway task-amend --help for flags.

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 · 25 lines · 0 tokens per session scan A c2cac5abc292

Subscribe to this mod's changes

task-amend is a command published in the GitHub repository thixpin/pitway (19 stars, last pushed 3d ago), licensed MIT. It adds 14 tokens to every session and 206 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.