Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Chappygo-OS/Atomic-Specnpx agentmods add commands/chappygo-os/atomic-spec/tasksWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/chappygo-os/atomic-spec/tasks)<a href="https://agentmods.dev/commands/chappygo-os/atomic-spec/tasks"><img src="https://agentmods.dev/badge/commands/chappygo-os/atomic-spec/tasks/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/chappygo-os/atomic-spec/tasks"><img src="https://agentmods.dev/badge/commands/chappygo-os/atomic-spec/tasks.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00021 | $0.10555 |
| Opus 5.5 | $0.00008 | $0.04222 |
| Sonnet 5.5 | $0.00004 | $0.02111 |
| Haiku 4.5 | $0.00002 | $0.01056 |
Grade C, and why
tasks scanned grade C with 2 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 1mo 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- Cross-Target Dependency Auto-Generation Rules: When generating tasks, automatically create dependency edges for these patterns: 1. API Producer/Consumer: If a backend task produces an endpoint (e.g., T-020 creates P Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s http://localhost:8000/api/feature/health | jq '.status == "ok"' How it starts
The opening of the file, as written. The whole thing — 1,072 lines — stays where its author put it; the contents beside it link to each section on GitHub.
User Input
$ARGUMENTS
You MUST consider the user input before proceeding (if not empty).
⛔ MANDATORY STRUCTURAL REQUIREMENTS
STOP. Read this section before generating ANY output.
Per Constitution Article IX, this command has NON-NEGOTIABLE constraints:
| Constraint | Required | Forbidden |
|---|---|---|
| Task storage | tasks/ directory with T-XXX-[name].md files |
Single tasks.md file |
| Dashboard | index.md in FEATURE_DIR |
No navigation file |
| Traceability | traceability.md mapping requirements ↔ tasks |
Unmapped tasks |
| Task content | All 4 elements (ID, Mapping, Detail, Verification) | Incomplete tasks |
If you are about to create a file called tasks.md, STOP. You are violating the Constitution.
Outline
1. Setup & Gate Compliance Check
Run {SCRIPT} from repo root. This script will:
- Parse FEATURE_DIR and AVAILABLE_DOCS list
- Automatically validate gate criteria (spec.md, plan.md, HITL approval)
- BLOCK execution if gates fail - you will see error output
If the script outputs gate failures, report them to the user and DO NOT PROCEED.
1.25 Phase 1 Prelude — Efficiency Hint (v0.4+) (advisory)
Run: atomicspec select-model --phase coordinator
If a non-empty model name is printed, the project has configured an advisory tier for coordinator-role turns like task generation; agents that support per-turn model selection (Claude Code subagent Task tool) MAY honor it. If the command prints nothing, advisor_enabled is false (v0.4 default) — proceed with default behavior; byte-for-byte v0.3 compatibility is preserved.
Advisory only: does not affect Directive 3 pinning (task generation is not yet under Context Pinning; that begins at /atomicspec.implement), gate criteria, atomic task naming (Directive 2), or embedded-context generation (Directive 8). Per-feature measurement lands in v0.4.1.
1.5 Load Project Defaults Registry
Per Constitution Article IX, Directive 7 - Load registry before generating tasks.
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.
- 1mo ago Changed · +37 lines d60431ce75c1
- 1mo ago First seen · 1,035 lines · 21 tokens per session scan C 94c04fba9870
tasks is a command published in the GitHub repository Chappygo-OS/Atomic-Spec (10 stars, last pushed 1mo ago), licensed MIT. It adds 21 tokens to every session and 10,555 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it C with 2 findings (hidden instructions, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
taskstoissues
A command that turns structured tasks from project design documents into ordered GitHub Issues, written in simplified Chinese.
ijfw-status
Show IJFW state -- mode, routing, memory, recent activity, codebase index, settings. Use when you want the at-a-glance banner you'd otherwise get at session start.
team
Manage your project's agent team. Usage: /team [setup|list|add|remove|swap].
workflow
Start or resume the IJFW project workflow. Usage: /workflow [discover|plan|execute|verify|ship|status].
implementation-plan
Define an incremental plan for the active task as IMPLEMENTATIONPLAN.md plus a TASKSTATE.md update: smallest safe slices with scope, validation and exit criteria. No code is written. A --spec mode derives slices from a spec or PRD. A retrofit mode annotates in-progress plans so they can adopt implement-fleet. Do not…
slice-closure
Decide whether the current slice is ready to close, separating slice completion from task completion, and record the result in slice notes and TASKSTATE.md. Use when a slice was implemented, validated or reviewed and may be ready to close. Do not use before slice implementation, during planning, or for overall task…