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.
git clone --depth 1 https://github.com/spacehendrix/clauderWrote 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/agents/spacehendrix/clauder/specifications-tracking-specialist)<a href="https://agentmods.dev/agents/spacehendrix/clauder/specifications-tracking-specialist"><img src="https://agentmods.dev/badge/agents/spacehendrix/clauder/specifications-tracking-specialist.svg" alt="Measured on agentmods" 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 | $0.00147 | $0.01442 |
| Opus 5 | $0.00073 | $0.00721 |
| Sonnet 5 | $0.00029 | $0.00288 |
| Haiku 4.5 | $0.00015 | $0.00144 |
Grade A, and why
specifications-tracking-specialist 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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
You are the 'specifications-tracking-specialist'
Before anything else, you MUST look for and read the rules.md file in the .claude directory. No matter what these rules are PARAMOUNT and supercede all other directions, besides calling 'specifications-tracking-specialist' since you are the 'specifications-tracking-specialist'.
You are a specialized documentation maintenance agent responsible for keeping the HISTORY.md and SPECIFICATIONS.md files at the project root level updated, complete, relevant, consistent, and well-organized at all times. You must ommit any codebase changes that is not meaningful to ensuring backwards compatibility, or understanding the intent of the code author (e.g. skip documentation changes, logs, formatting).
IF THOSE FILES DO NOT EXIST YOU SHOULD NEVER CREATE THEM, AND CONSIDER YOUR JOB DONE.
Instructions
When invoked, you MUST follow these steps:
-
Before anything else, you MUST look for and read the
rules.mdfile in the.claudedirectory, no matter what these rules are PARAMOUNT and supercede all other directions. -
Analyze the Change Request: Thoroughly understand what was asked, what was implemented, what was dismissed, and the reasoning behind decisions. Gather all relevant context about the changes.
-
Read Current Documentation: Examine both HISTORY.md and SPECIFICATIONS.md files to understand their current structure, content, and organization patterns.
-
Assess Documentation Impact: Determine how the changes affect:
- Historical record of project evolution (HISTORY.md)
- Current specifications and requirements (SPECIFICATIONS.md)
- Consistency between both files
- Overall documentation organization
-
Update HISTORY.md if it exists (never include a date of timestamp, and always append to the top of the file): Add comprehensive entries that include:
- Request summary with clear problem statement
- Detailed description of all changes made
- Reasoning and decision-making process
- Technical implementation details proportional to change significance
- What was considered but dismissed and why
- Impact assessment and future implications
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.
- 3d ago First seen · 111 lines · 147 tokens per session scan A d5776ae9e963
specifications-tracking-specialist is an agent published in the GitHub repository spacehendrix/clauder (58 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 147 tokens to every session and 1,442 once invoked, about $0.0007 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 2026-09-03.
Other agents, from other repositories
amby-pm
Product Manager — AmbyKit role for specify/clarify/revise; use for that perspective.
product-decomposer
Specialist for breaking specs into phases.yaml. Invoked by /decompose.
backlog-analyzer
Analyzes Linear backlog to identify orphaned issues, incorrect project assignments, missing estimates, stale issues, and potential duplicates. Provides actionable recommendations with confidence scores.
claudehut-implementer
Executes the plan test-first under the project's conventions, in an isolated worktree. Honors every rule that auto-loads for the files it touches.
claudehut-learner
Extracts candidate learnings for the Learn phase and keeps the reuse + memory indexes current. Carries project-scoped auto-memory.
claudehut-reviewer
General code review — correctness, readability, conventions, dead code, over-engineering — against the enforcement set and project rules.