Agent skill

Manifest

by Bonasa-Tech in Bonasa-Tech/manifest

A skill your agent uses when building, debugging, or integrating with the Manifest DEX on Solana, especially for TypeScript SDK usage, transaction construction with ManifestClient, market state…

GPL-3.0Auto-check passedDevelopment

Install Manifest

skills CLI
$ npx skills add Bonasa-Tech/manifest --skill manifest -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install Bonasa-Tech/manifest manifest --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/Bonasa-Tech/manifest.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/manifest .claude/skills/manifest && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
manifest
GitHub stars
158
Token cost
~478 tokens
SKILL.md length
191 words
Files
4 (incl. references)
Skills in repo
1
Repo updated
First seen
Licence
GPL-3.0

At a glance

A skill your agent uses when building, debugging, or integrating with the Manifest DEX on Solana, especially for TypeScript SDK usage, transaction construction with ManifestClient, market state…

  • Works in 4 steps: Identify whether the change is read-only… → For transaction changes, confirm setup… → Prefer composing instructions and… → …
  • Integrating with the Manifest DEX on Solana
  • SKILL.md covers Use This Skill When, First Steps, Standard Workflow and Validation Commands, plus 1 more section
  • Calls sh and cargo

What it does

Manifest is an agent skill from Bonasa-Tech/manifest. Use this skill when building, debugging, or integrating with the Manifest DEX on Solana, especially for TypeScript SDK usage, transaction construction with ManifestClient, market state reads via Market, and order/account-model decisions.

Its SKILL.md is about 480 tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files, including reference files (for example `agents/openai.yaml`, `references/manifest-actions.md` and `references/manifest-sdk.md`).

It sits in Development. It works with Solana and TypeScript. The repository describes itself as: The Spot CLOB on Solana. The licence is GPL-3.0.

When your agent uses it

  • Integrating with the Manifest DEX on Solana
  • Especially for TypeScript SDK usage
  • Transaction construction with ManifestClient
  • Market state reads via Market

Example prompts

  • “/manifest”

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. Identify whether the change is read-only market access (Market) or transaction-building (ManifestClient).
  2. For transaction changes, confirm setup path (getSetupIxs, seat/wrapper assumptions) before placing/canceling/withdrawing.
  3. Prefer composing instructions and returning them to caller boundaries.
  4. Validate with the smallest relevant test or command before broad test runs.

What it can do on your machine

Read from SKILL.md and the folder at commit 5718d3e. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • sh
    • cargo

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Manifest loads about 478 tokens when it runs, and up to ~2.7k if it reads all its reference files. Until then it costs about 63 tokens; SKILL.md has 191 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~63
When it runs · the whole SKILL.md, loaded when a task matches
~478
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2.7k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from Bonasa-Tech/manifest at commit 5718d3e, republished under its GPL-3.0 licence (© Bonasa-Tech). 191 words, ~478 tokens.

Download SKILL.mdSave it as .claude/skills/manifest/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
manifest
description
Use this skill when building, debugging, or integrating with the Manifest DEX on Solana, especially for TypeScript SDK usage, transaction construction with `ManifestClient`, market state reads via `Market`, and order/account-model decisions.

Manifest Skill

Use This Skill When

  • A task touches Manifest orderbook integrations, trading flows, or market reads.
  • You need to add or update TypeScript code using the Manifest SDK.
  • You need guidance on order types, wrapper/global accounts, or setup flows.
  • You need Bonasa-Tech Manifest repo commands for validation or implementation details.

First Steps

Primary guidance in this skill folder:

  • references/manifest-sdk.md

If working inside the Bonasa-Tech manifest repo:

  • SDK client changes: client/ts/src
  • SDK tests/examples: client/ts/tests
  • Rust AMM interface: client/rust/src
  • Program/runtime behavior: programs/

Reference files:

  • API quick map: references/manifest-sdk.md

Standard Workflow

  1. Identify whether the change is read-only market access (Market) or transaction-building (ManifestClient).
  2. For transaction changes, confirm setup path (getSetupIxs, seat/wrapper assumptions) before placing/canceling/withdrawing.
  3. Prefer composing instructions and returning them to caller boundaries.
  4. Validate with the smallest relevant test or command before broad test runs.

Validation Commands

  • If working in the Bonasa-Tech manifest repo, TypeScript client tests (local validator flow):
bash
sh local-validator-test.sh
  • If working in the Bonasa-Tech manifest repo, program tests:
bash
cargo test-sbf

Output Expectations

  • Reference exact files changed.
  • Keep behavior notes explicit for deposits, order placement, cancels, and withdrawals.
  • If assumptions are required (market address, token mints, signer model), state them clearly.

© Bonasa-Tech, GPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 3 other files (references) in skills/manifest of Bonasa-Tech/manifest.

  • SKILL.md
  • agents/openai.yaml
  • references/manifest-actions.md
  • references/manifest-sdk.md

Open the folder on GitHubat commit 5718d3e

Compare with similar skills

Manifest next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Manifest compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Manifest this skillBonasa-Tech/manifest158—~478Automated safety check: PassGPL-3.0
Pump TS Vanitynirholas/pump-fun-sdk134—~738Automated safety check: PassCustom licence
Pyth Network Price Feedsinternet-court/internet-court-skill6.6k2 repos~3.9kAutomated safety check: PassApache-2.0
Switchboard Oracle SDKinternet-court/internet-court-skill6.6k2 repos~2.9kAutomated safety check: PassApache-2.0
GLAM Solana Vault Managementinternet-court/internet-court-skill6.6k1 repos~1.8kAutomated safety check: PassApache-2.0
PNP Prediction Markets on Solanainternet-court/internet-court-skill6.6k—~7.5kAutomated safety check: NotesMIT

Similar skills

  • Pump TS Vanity

    nirholas/pump-fun-sdk

    Educational single-threaded TypeScript vanity address generator for Solana using @solana/web3.js with async iteration, event-loop yielding, streaming generator API, and best-effort memory zeroization.

    134 GitHub stars~738 tokensUpdated today
    DevelopmentAuto-check passed
  • Pyth Network Price Feeds

    internet-court/internet-court-skill

    Shows how to read Pyth oracle prices in Solana apps, off-chain through the Hermes client or on-chain from an Anchor program, including confidence and EMA values.

    6.6k GitHub starsUsed in 2 repos~3.9k tokens
    Backend & APIsAuto-check passed
  • Switchboard Oracle SDK

    internet-court/internet-court-skill

    Covers integrating Switchboard oracles on Solana: pull feeds, oracle quotes, VRF randomness and Surge WebSocket streaming, from both the TypeScript SDK and Rust.

    6.6k GitHub starsUsed in 2 repos~2.9k tokens
    Backend & APIsAuto-check passed
  • GLAM Solana Vault Management

    internet-court/internet-court-skill

    Creates and manages tokenized Solana vaults with the GLAM CLI and TypeScript SDK, including Jupiter swaps, Kamino lending, staking, access control and investor subscriptions.

    6.6k GitHub starsUsed in 1 repo~1.8k tokens
    Business, Finance & HRAuto-check passed
  • PNP Prediction Markets on Solana

    internet-court/internet-court-skill

    Creates, trades and settles permissionless prediction markets on Solana with any SPL token as collateral, including social-media and custom-oracle markets.

    6.6k GitHub stars~7.5k tokensUpdated 1 mo ago
    Business, Finance & HRAuto-check: notes
  • Rebuild Test

    metaDAOproject/programs

    Enforces rebuild and test workflow after code changes. An agent skill from metaDAOproject/programs.

    119 GitHub stars~433 tokensUpdated yesterday
    Business, Finance & HRAuto-check passed

Questions about Manifest

What does Manifest do?

A skill your agent uses when building, debugging, or integrating with the Manifest DEX on Solana, especially for TypeScript SDK usage, transaction construction with ManifestClient, market state…. Manifest is an agent skill from Bonasa-Tech/manifest. Use this skill when building, debugging, or integrating with the Manifest DEX on Solana, especially for TypeScript SDK usage, transaction construction with ManifestClient, market state reads via Market, and order/account-model decisions.

When should I use Manifest?

Manifest fits situations like: integrating with the Manifest DEX on Solana; especially for TypeScript SDK usage; transaction construction with ManifestClient; market state reads via Market.

How do I install Manifest in Claude Code?

Run `npx skills add Bonasa-Tech/manifest --skill manifest -a claude-code`. Or copy the skill folder (skills/manifest in Bonasa-Tech/manifest) into .claude/skills/manifest in your project. Claude Code loads it when a task matches its description.

How do I install Manifest in Codex?

Run `npx skills add Bonasa-Tech/manifest --skill manifest -a codex`. Or copy the skill folder (skills/manifest in Bonasa-Tech/manifest) into .agents/skills/manifest in your project. Codex loads it when a task matches its description.

Can I use Manifest in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Bonasa-Tech/manifest --skill manifest -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/manifest, .gemini/skills/manifest, .github/skills/manifest and .opencode/skills/manifest in your project.

What does Manifest need to run?

Going by SKILL.md and its folder, Manifest needs the command-line tools its instructions call (sh and cargo).

Does Manifest access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Manifest safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Manifest use?

Manifest is published under the GPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Manifest use?

About 478 tokens (SKILL.md is roughly 1.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 2.2k tokens, read only when the agent opens those files.

What are the alternatives to Manifest?

Skills that share tags, products or a category with Manifest: Pump TS Vanity (nirholas/pump-fun-sdk, 134 stars), Pyth Network Price Feeds (internet-court/internet-court-skill, 6.6k stars), Switchboard Oracle SDK (internet-court/internet-court-skill, 6.6k stars) and GLAM Solana Vault Management (internet-court/internet-court-skill, 6.6k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Manifest?

Bonasa-Tech (a GitHub organization) maintains it in Bonasa-Tech/manifest, which has 158 GitHub stars. The repository was last updated on October 9, 2026.

Source: Bonasa-Tech/manifest on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.