selfaware-task-update

A command that saves the current coding session's progress in a TASK_STATE.md file in the project root. The file acts as a checkpoint that can be read in a later session.

In plain words
What is it for?
Use it to record the current task, progress, usage snapshot, unfinished work, and next steps, especially before switching sessions or recovering interrupted work.
Why use it?
A checkpoint preserves what was completed, what is in progress, and what should happen next when a session ends or a usage limit interrupts the work. It also checks an existing checkpoint before updating it.

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/sorbh/claude-selfaware/selfaware-task-update
Clone the repo
git clone --depth 1 https://github.com/Sorbh/claude-selfaware
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 506 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 $0.00020 $0.00506
Opus 5 $0.00010 $0.00253
Sonnet 5 $0.00004 $0.00101
Haiku 4.5 $0.00002 $0.00051

Measured 2d ago against content hash 5841a8840f29, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

selfaware-task-update 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.

commands/selfaware-task-update.md · 55 lines

What it actually says

Create or update TASK_STATE.md in the current project root to checkpoint what we're working on right now, so the work survives a usage-limit reset or a fresh session. This is the manual version of what the skill does automatically at 90% usage.

Steps:

  1. Run ~/.claude/skills/selfaware/scripts/usage-check.sh to get a usage snapshot for the header (5h %, 7d %, resets_at).

  2. If TASK_STATE.md already exists, READ it first. If it describes a different task than what we're currently doing, STOP and tell the user — do not overwrite it. Ask whether to replace it or save the checkpoint somewhere else. (This guard exists because TASK_STATE.md is a single fixed file per directory.)

  3. Otherwise write/update TASK_STATE.md using this structure, filled from the actual current session state (not a template — real values):

    # Task State Checkpoint
    > Saved at: <timestamp>
    > Usage: <5h>% (5h) / <7d>% (7d)
    > Resets at: <resets_at>
    
    ## Task
    <one-line goal>
    
    ## Status: IN_PROGRESS
    
    ## Done
    - <completed items, specific enough to verify>
    
    ## In Progress
    - <what's mid-flight and its exact current state>
    
    ## Next Steps
    1. <exact next action — specific enough for a fresh session>
    
    ## Files Touched
    - `path/to/file` — <what changed>
    
    ## Resume Instructions
    <what to do first when resuming>
    
  4. Keep it concrete — file paths, line numbers, commands. Bad: "was working on auth." Good: "added JWT verify to src/auth.ts:45-80, untested; next: npm test -- auth."

  5. Tell the user the checkpoint is saved and where.

If the user passed text in $ARGUMENTS, fold it into the checkpoint as extra context/notes.

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 · 55 lines · 20 tokens per session scan A 5841a8840f29

Subscribe to this mod's changes

selfaware-task-update is a command published in the GitHub repository Sorbh/claude-selfaware (2 stars, last pushed 1mo ago), licensed MIT. It adds 20 tokens to every session and 506 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 2026-08-31.