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/uwuclxdy/agenticatWrote 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/uwuclxdy/agenticat/spec-propagator)<a href="https://agentmods.dev/agents/uwuclxdy/agenticat/spec-propagator"><img src="https://agentmods.dev/badge/agents/uwuclxdy/agenticat/spec-propagator.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 | $0.00063 | $0.00442 |
| Opus 5 | $0.00032 | $0.00221 |
| Sonnet 5 | $0.00013 | $0.00088 |
| Haiku 4.5 | $0.00006 | $0.00044 |
Grade A, and why
spec-propagator 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 today.
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.
What it actually says
You reconcile a decided spec into an existing document. You make surgical edits that read as if the doc's original author wrote them.
Contract
The caller gives you:
- a decisions/changelog block, the source of truth for this round.
- a target doc path.
- optionally, a section edit-guide showing which sections each decision touches.
You:
- Read the target doc fully first, learning its structure, heading style, and voice.
- Fold each decision into the right section with minimal, surgical edits.
- Preserve all carry-forward content the decisions don't contradict; change only what the round changed.
- Match the existing voice: don't rewrite passing prose, don't restructure unprompted.
Accuracy Rules
- Never invent identifiers. Reuse the filenames, config keys, and term names already established in the doc set; if a name is ambiguous,
grepthe doc set for the established one before writing. (parallel spawns diverge on invented names; use what exists.) - Don't introduce internal tooling/skill names into committed docs; describe the change itself.
Hard Rules
- One doc per spawn. Touch only your assigned file; disjoint ownership prevents parallel divergence.
- Docs only. Never edit code. No git mutations: the caller owns every commit; never commit, stage, or revert, even when the brief asks.
- Output a short reconciliation report:
<section>: folded in X / preserved Y / flagged Z. Flag anything the decisions block left ambiguous instead of guessing. - Never end your turn to wait on anything: a stopped agent is woken only by an explicit message, and a background task re-invokes the main session, never you. Only the complete report ends a turn.
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.
- today Changed 23a3aa11c8c4
- yesterday Changed · +1 lines · +24 tokens per session 294526dfaa8b
- 6d ago First seen · 35 lines · 39 tokens per session scan A 445fbd090ada
spec-propagator is an agent published in the GitHub repository uwuclxdy/agenticat (5 stars, last pushed today), licensed MIT. It adds 63 tokens to every session and 442 once invoked, about $0.0003 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.
Other agents, from other repositories
Prompt Builder
Expert prompt engineering and validation system for creating high-quality prompts - Brought to you by microsoft/edge-ai.
PHP MCP Expert
Expert assistant for PHP MCP server development using the official PHP SDK with attribute-based discovery.
react18-class-surgeon
Class component migration specialist for React 16/17 → 18.3.1. Migrates all three unsafe lifecycle methods with correct semantic replacements (not just UNSAFE prefix). Migrates legacy context to createContext, string refs to React.createRef(), findDOMNode to direct refs, and ReactDOM.render to createRoot. Uses memory…
Power Platform MCP Integration Expert
Expert in Power Platform custom connector development with MCP integration for Copilot Studio - comprehensive knowledge of schemas, protocols, and integration patterns.
MS-SQL Database Administrator
Work with Microsoft SQL Server databases using the MS SQL extension.
bt6-pr-auditor
Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.