# Wild Manual > Fixed-scope research, reliable agent workflows, and interface systems with visible checks and a clean handoff. Wild Manual is Kiren Srinivasan's independent practice and brand. It sells fixed-scope work with visible acceptance checks and a documented handoff. ## Primary pages - [Offers](https://wildmanual.com/offers/): Prices, scope, checks, and exclusions - [Work](https://wildmanual.com/work/): Public repositories and stated limits - [Method](https://wildmanual.com/method/): Gate, build, verify, and handoff - [Field notes](https://wildmanual.com/field-notes/): Dated, sourced working notes - [Start a project](https://wildmanual.com/contact/): Human inquiry form and email fallback - [Offers JSON](https://wildmanual.com/offers.json): Structured offer records - [Offers Markdown](https://wildmanual.com/offers.md): Text version of all offers - [OpenAPI](https://wildmanual.com/openapi.json): Current public API contract - [Security](https://wildmanual.com/security/): Access and reporting practices - [Privacy](https://wildmanual.com/privacy/): Inquiry data handling ## Rules - Public prices, exclusions, seller identity, and policies are the same for people and software. - Public GET routes are read-only. - Submission does not accept a project or authorize spending. - Consequential actions require written authority and the same server-side validation used by human paths. - Marketplace-originated work stays on that marketplace. Wild Manual is the independent practice and brand of Kiren Srinivasan. Payment documents name the legal seller shown in the written scope and invoice. # Offers ## 72-hour Field Test One bounded question answered with evidence, risks, a first useful slice, and a fixed follow-on scope. - Price: $1,500 to $2,500 - Delivery: 72 hours after inputs are complete - URL: https://wildmanual.com/offers/field-test/ ### Finished artifact A decision-ready map that is useful even if no larger project follows. ### Included - Written question and finish line - Current-state and dependency map - Human and agent responsibility boundary - Risk, access, and approval map - One recommended first slice - Acceptance criteria and fixed follow-on scope - Markdown, PDF-ready source, and structured JSON - One written revision round ### Acceptance checks - Every material claim traces to a source or is labeled as an assumption - Contradictions and unknowns remain visible - The first slice has a clear stop condition - The buyer can use the map without commissioning the build ### Excluded - Production code - Live integrations - Security or compliance certification - Open-ended advisory access --- ## Research Field Guide A decision-ready dossier with primary sources, contradictions, and a recommended path. - Price: From $2,500 - Delivery: 3 to 5 business days - URL: https://wildmanual.com/offers/research-field-guide/ ### Finished artifact A cited field guide for a product, market, protocol, vendor, or strategy decision that matters this month. ### Included - Written question and kill criteria - Primary-source map - Relevant market, competitor, product, or protocol evidence - Contradictions and unknowns - Decision matrix and recommended path - Markdown, PDF-ready source, and source ledger - One written revision round ### Acceptance checks - Every material claim traces to a dated source - Source ownership is visible - Contradictory evidence is retained - Assumptions and the condition that would reverse the recommendation are named ### Excluded - Ongoing monitoring - Licensed legal or financial advice - Paid interviews - Research that requires prohibited scraping or deception --- ## Agent Workflow Sprint One unreliable workflow turned into a tested agent-assisted path with permissions, recovery, and a runbook. - Price: From $5,000 - Delivery: 5 to 10 business days - URL: https://wildmanual.com/offers/agent-workflow-sprint/ ### Finished artifact A working workflow with a human control point, clear stop conditions, and proof that failure does not create duplicate work. ### Included - Current-state map and failure inventory - One narrow production workflow - Tool or protocol integration only where justified - Least-privilege access and secret handling - Happy-path, recovery, rejection, and refusal tests - Deployment or local runbook - One written or recorded handoff ### Acceptance checks - Repeated requests are idempotent - Consequential outward actions have an explicit checkpoint - Known failures stop cleanly and produce a useful error - No secret appears in source or logs - The agreed suite passes in the target environment ### Excluded - Open-ended platform ownership - Unsupervised spending - Bulk cold outreach - Sensitive production access before payment and written authorization --- ## Interface System Rescue A coherent token system and the priority surfaces needed to ship it across devices. - Price: From $4,500 - Delivery: 5 to 8 business days - URL: https://wildmanual.com/offers/interface-system-rescue/ ### Finished artifact A small interface system with implemented priority screens, explicit rules, and a before, after, and why record. ### Included - Visual and interaction audit grounded in real screens - Primitive, semantic, and component tokens - Priority-screen redesign and implementation - Responsive, keyboard, contrast, and reduced-motion checks - Measured performance pass - Before, after, and why report ### Acceptance checks - Product components do not contain raw color values - Text and meaningful UI contrast checks pass - The critical journey works at 375 pixels and desktop - Tested layout shift stays below 0.1 - Every retained motion rule communicates a named state or relationship ### Excluded - Full rebrands - Large design-system migrations - Custom illustration libraries - Unlimited screen production # Method ## 01 Name the finish line You should know the finish line before I touch the work. We name the file, screen, decision, or working path that must exist at handoff. ## 02 Inspect the field conditions I inspect the actual sources and permissions before asking for more access. That is where constraints and failure cases usually surface. ## 03 Build the smallest deep solution I build the smallest version that answers the question or makes the path work. Protocols and polish wait until they earn their place. ## 04 Try to break it Then I try the obvious breakpoints: bad input, a rejection, an interruption, and a repeat request. The agreed checks decide whether it is ready. ## 05 Hand over the artifact and the manual You get the artifact, its source, the checks I ran, the limits I found, and a manual someone else can follow. # Public work ## webular An open-source web research CLI that routes focused capabilities through a deterministic task graph. - Status: Public repository, versioned release - Repository: https://github.com/srinitude/webular ### Verified facts - Commands cover search, scrape, crawl, map, extract, research, monitoring, browser action, and MCP access - Machine data goes to standard output and logs go to standard error - The task graph owns setup, formatting, type checks, build, tests, validation, and CI - The project is published under Apache-2.0 ### Limits - No client adoption or revenue claim is made - Third-party websites and services can still change or block access --- ## Visual Design System Extractor A portable Agent Skills package that converts visual evidence into a validated design-system contract. - Status: Public repository, validation workflow present - Repository: https://github.com/srinitude/visual-design-system-extractor ### Verified facts - Accepts screenshots, moodboards, product UI, brand boards, and other visual evidence - Produces parser-valid YAML with confidence labels and reusable tokens - Includes schema and package validators - The project is published under Apache-2.0 ### Limits - Extraction describes evidence; it does not grant rights to copy a reference identity - Human review still owns taste, originality, and implementation decisions --- ## Hermes Toolbox Public, reusable agent building blocks with explicit sanitization, identity-neutrality, and safety checks. - Status: Public repository, validators documented - Repository: https://github.com/srinitude/hermes-toolbox ### Verified facts - Packages public-safe skills, profiles, plugins, scripts, and workflow primitives - Separates shareable templates from private runtime state - Documents target paths, prohibited write surfaces, and validation thresholds - Includes public-safety, identity-neutrality, and tutorial validators ### Limits - A public template is not a copy of a live private profile - Users must review and explicitly enable plugins in their own target environment # Field notes ## The human approval is the product boundary Published: 2026-07-10 The valuable part of an agent workflow is often the place where evidence becomes a decision and a person can still say no. ### Buyers are asking for controlled work, not magic Public briefs from legal, healthcare-adjacent, and service businesses keep circling the same need. Make the tools talk. Keep sensitive data inside a written boundary. Give a person enough evidence to stop an uncertain or consequential action. MCP might be right. So might a plain API, browser automation, or none of them. The buyer is not purchasing a protocol; they need a workflow that still holds up when the demo conditions disappear. ### The demo should survive four ordinary failures The happy path only proves that the demo can work once. I also want to see what happens when someone says no, a run is interrupted, a request repeats, or the input is unusable. - The reviewer can say no or change the proposed action - An interrupted run resumes instead of quietly starting over - A repeated request cannot create another write or charge - Unusable input stops at the right point and names the next step ### The interface is part of the safety system A confirmation dialog at the end is not approval. Put the proposed action, the evidence behind it, the cost, and the affected account where the reviewer can see them before choosing what happens next. That small surface is where the workflow becomes accountable. ### The rule Count the boundary and the verification work, not the agents. The buyer is paying for an artifact they can run after handoff. --- ## One contract, two surfaces Published: 2026-07-10 A human page and a machine-readable route should expose the same offer, price, limits, and owner. ### The human surface comes first The public website has to work on its own. A buyer should be able to understand the offer and the seller, inspect proof, send an inquiry, and print the terms without JavaScript. An agent should not be required for any of that. Semantic HTML is the contract’s first published form, not a degraded fallback. ### Machine readability removes guessing Software should not have to scrape a marketing page when a clean record will do. Markdown, JSON, feeds, and OpenAPI can restate the same facts, but they do not get hidden claims or a lower price. - Generate each public representation from the same content record - Let public GET routes read, never write - Publish OpenAPI only after the documented routes work - Skip empty Agent Cards and speculative discovery files ### A protocol is earned by a capability A protocol should answer a real need. MCP makes sense when a callable tool exists. A2A needs a long-running service with task state and cancellation. Machine payment needs a repeatable digital output and a refund path we have actually tested. If those capabilities do not exist yet, say so. A clear site, a written scope, and an ordinary invoice are more useful than protocol theater. # Contact and authority Email: kiren@fantasymetals.com AI helps with production. Kiren makes the final call on scope, evidence, exceptions, and release. If work begins on a marketplace, communication and payment stay on that marketplace.