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 ChipAlexandru/strategy-consultant --skill synthesisgit clone --depth 1 https://github.com/ChipAlexandru/strategy-consultantWrote 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/chipalexandru/strategy-consultant/synthesis)<a href="https://agentmods.dev/skills/chipalexandru/strategy-consultant/synthesis"><img src="https://agentmods.dev/badge/skills/chipalexandru/strategy-consultant/synthesis/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/chipalexandru/strategy-consultant/synthesis"><img src="https://agentmods.dev/badge/skills/chipalexandru/strategy-consultant/synthesis.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 | $0.00099 | $0.03891 |
| Opus 5 | $0.00049 | $0.01946 |
| Sonnet 5 | $0.00020 | $0.00778 |
| Haiku 4.5 | $0.00010 | $0.00389 |
Grade A, and why
synthesis 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 10d 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 — 250 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Synthesis — Build the Storyline
Synthesis is not summarizing. Summarizing says "here is what the data shows." Synthesis says "here is what it means for the client's decision — and here is what they should do."
Take the validated, sense-checked research findings and organize them into the storyline that most directly and persuasively answers the client question.
Preflight Gate (run BEFORE any other step)
This phase requires upstream state and artifacts. Before doing anything else, verify ALL of the following:
engagement-state.jsonexists in the active workspace."sense-check"is incompleted_phases.- The following artifacts exist on disk and are non-empty:
sense-check.mdresearch-validated.mdprecision-anchor.md
If ANY required item is missing or empty, STOP. Do not write a governing message, do not draft headlines, do not produce a storyline. Report the specific missing state field or artifact path and route control back to engagement-manager. A storyline written without a passed sense-check is the most dangerous failure mode in this plugin — it converts un-pressure-tested findings into persuasive narrative.
Additionally, before proceeding, read sense-check.md and confirm the Question-Answer Precision Verdict is PRECISE or PARTIAL. If the verdict is DRIFTED, STOP — the engagement-manager must loop back to research, not forward to synthesis.
When the gate passes:
- Read
engagement-state.jsonand treat itsworkspace_pathas the active workspace. - Use
precision-anchor.mdas the authoritative reference for Step 0 (Precision Anchor Re-Check) and the governing message altitude test. - Use
research-validated.mdas the evidence base; treat its CS scores and alignment markers ([DIRECT]/[SUPPORTING]/[ADJACENT]) as authoritative. - Use
sense-check.mdfor the steel-man counter-narrative, Client-Raised Objections Inventory, Evidence-Implied Risks, and Value-Add Opportunities.
At the end of this phase, append "synthesis" to completed_phases, update artifact_paths.storyline, set current_phase to storyline-critique, refresh next_required_action and last_updated, and write engagement-state.json.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 250 lines · 99 tokens per session scan A 2c0c824d8293
synthesis is a skill published in the GitHub repository ChipAlexandru/strategy-consultant (4 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 99 tokens to every session and 3,891 once invoked, about $0.0005 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…