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.
npx skills add hybridlabor-api/bdb-dev-optimized-agent-skills --skill td-feature-synthesizegit clone --depth 1 https://github.com/hybridlabor-api/bdb-dev-optimized-agent-skillsWrote 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/skills/hybridlabor-api/bdb-dev-optimized-agent-skills/td-feature-synthesize)<a href="https://agentmods.dev/skills/hybridlabor-api/bdb-dev-optimized-agent-skills/td-feature-synthesize"><img src="https://agentmods.dev/badge/skills/hybridlabor-api/bdb-dev-optimized-agent-skills/td-feature-synthesize/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/skills/hybridlabor-api/bdb-dev-optimized-agent-skills/td-feature-synthesize"><img src="https://agentmods.dev/badge/skills/hybridlabor-api/bdb-dev-optimized-agent-skills/td-feature-synthesize.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 | $0.00105 | $0.01379 |
| Opus 5 | $0.00053 | $0.00690 |
| Sonnet 5 | $0.00021 | $0.00276 |
| Haiku 4.5 | $0.00011 | $0.00138 |
Grade A, and why
td-feature-synthesize 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 12d 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.
This is a copy
100% identical to td-feature-synthesize — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
td-feature-synthesize — merge, reconcile, prioritize
You consolidate up to five independent surveys into the single artifact the user wants: an honest, prioritized list of new features, organized by surface, ranked by value vs. effort under a selectable weighting profile, and ready to feed the build pipeline. Surveyors brought vetted depth; you bring judgment.
Procedure
1. Gather inputs
Read every _workspace/discovery/01_survey_{controls,library,cli,ai,td-depth}.md that exists, plus docs/ROADMAP.md, AGENTS.md, CHANGELOG.md, and the project-td-mcp-competitive-landscape memory if present. If a survey is missing, proceed and record the gap in a coverage line.
2. Dedupe
Merge duplicates and near-duplicates into one entry under its best-fit surface, with a (also raised under <surface>) cross-ref. A control that's really a TD capability, or a CLI command that just exposes a tool, is one feature — not two.
3. Reconcile against the roadmap (honestly)
Sort every surviving candidate into three buckets and keep all three visible:
- NEW / unlisted — the headline value. These are what the user can't already see in the roadmap.
- Already planned — cite the phase (Phase 13 / deferred-v0.6.0+). Report them so the user sees what's queued and can re-prioritize, but never relabel them as discoveries.
- Extensions — concrete extensions of shipped tools/commands/prompts.
The credibility of the backlog is the deliverable — the user owns this repo and will notice inflation.
4. Prioritize
Score each item on impact (High/Med/Low) × effort (S/M/L), then assign a single priority:
| S effort | M effort | L effort | |
|---|---|---|---|
| High impact | P0 (quick win) | P0 | P1 |
| Med impact | P1 | P1 | P2 |
| Low impact | P2 | P2 | P2 (trap — flag it) |
Weighting profile. How you weight impact is the most consequential call you make. Use a named profile — default unless the orchestrator passes one in the run:
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.
- 12d ago First seen · 94 lines · 105 tokens per session scan A 701693543835
td-feature-synthesize is a skill published in the GitHub repository hybridlabor-api/bdb-dev-optimized-agent-skills (6 stars, last pushed 7d ago), licensed Apache-2.0. It adds 105 tokens to every session and 1,379 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to td-feature-synthesize, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
agent-workflow-automation
Agent skill for workflow-automation - invoke with $agent-workflow-automation.
agent-pseudocode
Agent skill for pseudocode - invoke with $agent-pseudocode.
agent-trading-predictor
Agent skill for trading-predictor - invoke with $agent-trading-predictor.
agent-performance-analyzer
Agent skill for performance-analyzer - invoke with $agent-performance-analyzer.
embeddings
Vector embeddings with HNSW indexing, sql.js persistence, and hyperbolic support. 75x faster with agentic-flow integration. Use when: semantic search, pattern matching, similarity queries, knowledge retrieval. Skip when: exact text matching, simple lookups, no semantic understanding needed.
mcp-host-styling-integration
Integrates MCP App UI with host theming system. Applies host CSS variables, handles onhostcontextchanged, safe area insets, display mode detection, and fullscreen configuration.