TaskTracker

TaskTracker is an agent for coding agents from attilaszasz/sdd-pilot. It costs 21 tokens per session (1,606 once invoked), scanned A, original, MIT.

A task-file parser that reads tasks.md and turns recognized checklist entries into structured task data, including their status and metadata.

In plain words
What is it for?
Use it to load a feature's tasks into tools that need machine-readable task lists, such as planners, dashboards, or automated workflows.
Why use it?
It removes the need to manually interpret task checkboxes and tags. Invalid task entries are ignored safely, while missing or empty files produce an empty list.

Agent

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 agents/attilaszasz/sdd-pilot/_task-tracker
Clone the repo
git clone --depth 1 https://github.com/attilaszasz/sdd-pilot

Wrote 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.

agentmods badge for TaskTracker

README.md
[![agentmods](https://agentmods.dev/badge/agents/attilaszasz/sdd-pilot/_task-tracker.svg)](https://agentmods.dev/agents/attilaszasz/sdd-pilot/_task-tracker)
Your own site
<a href="https://agentmods.dev/agents/attilaszasz/sdd-pilot/_task-tracker"><img src="https://agentmods.dev/badge/agents/attilaszasz/sdd-pilot/_task-tracker.svg" alt="Measured on agentmods" height="20"></a>
Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,606 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 $0.00021 $0.01606
Opus 5 $0.00010 $0.00803
Sonnet 5 $0.00004 $0.00321
Haiku 4.5 $0.00002 $0.00161

Measured 4d ago against content hash a9641df360ed, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

TaskTracker 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 4d 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/agents/_task-tracker.md · 122 lines

How it starts

The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Task

Parse tasks.md into structured task objects with status metadata.

Inputs

Feature directory containing tasks.md.

Execution Rules

Preserve order, infer status consistently, fail closed on malformed task candidates, and return machine-readable output only.

Output Format

Return a single JSON array of parsed task objects for valid input. Return one JSON error object for invalid input.

  1. Read FEATURE_DIR/tasks.md. If missing or empty → return [].
  2. Run node scripts/parse-tasks.mjs "FEATURE_DIR/tasks.md" from the repository root and parse its JSON output. This parser recognizes these two accepted forms:
  • Standard task: - [ |X|x] T### [P?] [US#|OBJ#?] {(FR|TR|OR|RR)-###?} [COMPLETES req?] Description [after:T###?] [← T###:Symbol?] [→ exports: Symbol?] [VERIFY: <command>]?*
  • QC bug task: - [ |X|x] T### [BUG:severity] [RECURRING?] [ESCALATED?] [DEFERRED?] {(FR|TR|OR|RR)-###?} [category?] Description
  • Checkbox: [ ]=pending, [X]/[x]=completed
  • ID: T###
  • Optional [P] → parallel=true
  • Optional [US#]/[OBJ#] → workItem, story, objective
  • Optional [BUG:CRITICAL|ERROR|WARNING]bugSeverity
  • Optional modifier tags [RECURRING], [ESCALATED], [DEFERRED]modifiers array and deferred boolean
  • Optional [category] after requirement tags on bug tasks → bugCategory
    • Optional {FR-###}, {TR-###}, {OR-###}, {RR-###} (comma-separated) → requirements array
    • Extract filePath from the task description when a path is present
    • Optional [COMPLETES (FR|TR|OR|RR)-###]completesRequirement string (e.g. "FR-003")
    • Optional after:T### (comma-separated for multiple) → dependencies array (e.g. ["T005", "T008"])
      • Optional ← T###:Symbol,Symbolimports array of {"sourceTask": "T###", "filePath": "src/example.ts", "symbols": ["Symbol"]} objects when the source task can be resolved from the parsed task list
      • Optional ← plan:AcceptanceTestStubsimports entry of {"sourceTask": "plan", "filePath": null, "symbols": ["AcceptanceTestStubs"]} marking this as an acceptance test stub task; the Developer reads the ## Acceptance Test Stubs section from plan.md directly (no task ID to resolve, filePath stays null)
    • Optional → exports: Symbol(params),Symbolexports array of symbol strings
    • Optional [VERIFY: <command>] (repeatable; zero or more) → verify array of command strings. The command MUST be non-empty and MUST NOT contain a literal ]. Commands run from the repo root.
    • Remaining text (after removing parsed annotations) → description
  • Current heading → phase
    • After parsing all tasks, resolve dependencies and imports[].filePath by matching referenced task IDs to parsed tasks in the same tasks.md
  • Include completed tasks. Ignore non-task prose, headings, and checkbox lines whose first token is not task-like. Preserve order.
  • A checkbox line with a task-like first token (T...) is a task candidate. Invalid checkbox state, T### ID, requirement, dependency, import, export, or VERIFY annotation is a parse error, never an ignored line.
  1. If parser output has valid: false, a non-empty errors array, invalid JSON, or a non-zero exit, return exactly {"tasks": [...], "parseErrors": [{"line": 12, "code": "invalid-task-id", "message": "invalid task ID T12; expected T###", "source": "- [ ] T12 ..."}]} using the parser's partial tasks and errors. Do not return a bare array or continue with partial parsing.
  2. For valid parser output, return only its tasks value as the stable single JSON array:

Read the full file on GitHub · 122 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. 4d ago First seen · 122 lines · 21 tokens per session scan A a9641df360ed

Subscribe to this mod's changes

TaskTracker is an agent published in the GitHub repository attilaszasz/sdd-pilot (95 stars, last pushed today), licensed MIT. It adds 21 tokens to every session and 1,606 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.

Related

Other agents, from other repositories

performance-optimizer

Performance analysis and optimization specialist. Use PROACTIVELY for identifying bottlenecks, optimizing slow code, reducing bundle sizes, and improving runtime performance. Profiling, memory leaks, render optimization, and algorithmic improvements.

Jamkris/everything-gemini-code · 48 tokens

security-reviewer

Security vulnerability detection and remediation specialist. Use PROACTIVELY after writing code that handles user input, authentication, API endpoints, or sensitive data. Flags secrets, SSRF, injection, unsafe crypto, and OWASP Top 10 vulnerabilities.

Jamkris/everything-gemini-code · 52 tokens

python-reviewer

Expert Python code reviewer specializing in PEP 8 compliance, Pythonic idioms, type hints, security, and performance. Use for all Python code changes. MUST BE USED for Python projects.

Jamkris/everything-gemini-code · 43 tokens

a11y-architect

Accessibility Architect specializing in WCAG 2.2 compliance for Web and Native platforms. Use PROACTIVELY when designing UI components, establishing design systems, or auditing code for inclusive user experiences.

Jamkris/everything-gemini-code · 45 tokens

gan-evaluator

GAN Harness — Evaluator agent. Tests the live running application via Playwright, scores against rubric, and provides actionable feedback to the Generator.

Jamkris/everything-gemini-code · 32 tokens

opensource-forker

Fork any project for open-sourcing. Copies files, strips secrets and credentials (20+ patterns), replaces internal references with placeholders, generates .env.example, and cleans git history. First stage of the opensource-pipeline skill.

Jamkris/everything-gemini-code · 51 tokens