Agent skill

Economic Design Audit

by PlamenTSV in PlamenTSV/plamen

Trigger Pattern MONETARYPARAMETER flag (fee, rate, emission, cap, bps as template fields) - Inject Into Breadth agents (merged via M4 hierarchy)

MITAuto-check passedMedia & Creative

Install Economic Design Audit

skills CLI
$ npx skills add PlamenTSV/plamen --skill economic-design-audit -a claude-code

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

GitHub CLI
$ gh skill install PlamenTSV/plamen economic-design-audit --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/PlamenTSV/plamen.git skills-src && mkdir -p .claude/skills && cp -r skills-src/agents/skills/daml/economic-design-audit .claude/skills/economic-design-audit && 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
economic-design-audit
GitHub stars
303
Token cost
~2.2k tokens
SKILL.md length
892 words
Files
1
Skills in repo
87
Repo updated
First seen
Licence
MIT

At a glance

Trigger Pattern MONETARYPARAMETER flag (fee, rate, emission, cap, bps as template fields) - Inject Into Breadth agents (merged via M4 hierarchy)

  • Works in 5 steps: Parameter Boundary Analysis → Economic Invariant Identification → Accumulator / Cap Coherence Across… → …
  • Pattern MONETARYPARAMETER flag (fee
  • SKILL.md covers 1. Parameter Boundary Analysis, 2. Economic Invariant…, 3. Accumulator / Cap Coherence… and 4. Fee / Rate Formula…, plus 3 more sections
  • Needs NO_SUCH_KEY

What it does

Economic Design Audit is an agent skill from PlamenTSV/plamen. Trigger Pattern MONETARYPARAMETER flag (fee, rate, emission, cap, bps as template fields) - Inject Into Breadth agents (merged via M4 hierarchy)

Its SKILL.md is about 2.2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Media & Creative, covering Design review and critique. The repository describes itself as: Autonomous Web3 security audit agent for Claude Code. The licence is MIT.

When your agent uses it

  • Pattern MONETARYPARAMETER flag (fee
  • Bps as template fields) - Inject Into Breadth agents (merged via M4 hierarchy)

Example prompts

  • “/economic-design-audit”

Requirements

  • A credential in NO_SUCH_KEY

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Parameter Boundary Analysis
  2. Economic Invariant Identification
  3. Accumulator / Cap Coherence Across Transactions (R14 — PRIMARY DAML LANE)
  4. Fee / Rate Formula Verification at Normal Values
  5. Emission / Inflation Sustainability

What it can do on your machine

Read from SKILL.md and the folder at commit 795962b. 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

    No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).

    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 these keys or tokens, usually read from environment variables:

    • NO_SUCH_KEY

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

Context cost

Economic Design Audit loads about 2.2k tokens when it runs. Until then it costs about 42 tokens; SKILL.md has 892 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~42
When it runs · the whole SKILL.md, loaded when a task matches
~2.2k

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 PlamenTSV/plamen at commit 795962b, republished under its MIT licence (© PlamenTSV). 892 words, ~2,209 tokens.

Download SKILL.mdSave it as .claude/skills/economic-design-audit/SKILL.md (or your agent's skills folder).
name
economic-design-audit
description
Trigger Pattern MONETARY_PARAMETER flag (fee, rate, emission, cap, bps as template fields) - Inject Into Breadth agents (merged via M4 hierarchy)

ECONOMIC_DESIGN_AUDIT Skill (DAML)

Trigger Pattern: MONETARY_PARAMETER flag (required) Inject Into: Breadth agents (merged via M4 hierarchy) Finding prefix: [DML-EDA-N] Rules referenced: R2, R10, R13, R14

rate|fee|reward_rate|emission|inflation|cap|limit|max_amount|basis_points|bps|fee_bps|spread|price|amount

DAML arithmetic context: monetary values are template fields typed Int or Decimal (Decimal = fixed-point, 10 fractional digits). There is no floating-point. A "setter" is a choice that archives a config/parameter contract and creates a successor with a changed field; a "consumer" is any choice/ensure that reads that field and branches. Critical DAML difference: Int/Decimal THROW on overflow — they do not wrap. So an economic boundary that overflows is a liveness/brick bug (the choice aborts, the path becomes un-exercisable), never a silent-value bug. Division truncates toward zero.


1. Parameter Boundary Analysis

For every monetary parameter (a config/parameter template field set by a choice — rate, fee, reward rate, emission, cap, floor, BPS):

Parameter (Template.field)Setting ChoiceMin ValueMax Valueensure-Enforced?Impact at MinImpact at Max

For each: substitute min and max into ALL consuming choices. Tag: [BOUNDARY:param=val -> outcome]

DAML-specific boundary checks:

  • Does MAX cause an Int/Decimal overflow in amount * rate BEFORE the division? An overflow ABORTS the choice → liveness brick ([ELEVATE:ENSURE_GAP]/boundary), not a wrap.
  • Does 0 cause a division-by-zero? In DAML that ABORTS the transaction → verify a guard or ensure blocks zero.
  • Does 10000 bps (100%) make the holder receive 0 (truncated) or, with fees-on-fees, push a successor's ensure to fail (PreconditionFailed)?
  • Does a negative field value slip past a missing ensure? (Int/Decimal are signed; ensure amount > 0.0 is the only guard.)

2. Economic Invariant Identification

List all economic invariants the protocol must maintain, and whether a setter choice can break them:

InvariantParameters InvolvedCan a Setter Choice Break It?Choices That Assume It

For each setter: can creating a successor with a changed field break an invariant a consuming choice depends on? If yes → finding.

DAML-specific invariants:

  • Value conservation across split/merge/transfer: total carried by all child contracts must equal the parent. Verify no rounding loss accumulates across many split operations (Decimal truncation).
  • No negative amounts: only an ensure amount >= 0.0 prevents a negative-amount contract entering the ACS; without it the create succeeds and every downstream choice trusts a broken invariant.
  • Accumulator/cap honored across transactions: see Section 3 — this is the highest-yield DAML economic class.

3. Accumulator / Cap Coherence Across Transactions (R14 — PRIMARY DAML LANE)

DAML has no global mutable counter; a cap/total is itself a contract whose field is updated by a choice. The recurring bug: a value-creating choice does NOT update the accumulator contract, so the cap is never enforced across transactions.

Cap/Total (Template.field)Updated By (choices)Read/Enforced By (choices)Every Value-Creating Path Updates It?Finding?

Check (R14 cross-variable + constraint coherence + setter regression):

  • Is there a value-creating choice (mint/issue/Propose-Accept) that creates an asset contract but does NOT archive+recreate the cap/total contract to reflect it? → cap unenforced → unbounded issuance ([ELEVATE:VALUE_CONSERVATION]).
  • Are two interacting limits (per-tx cap and global cap) settable by independent choices without a coherence check between them?
  • Can a setter choice lower the cap field BELOW the already-accumulated total? What does the consuming ensure/guard do then (abort? lock out all holders?) — setter regression.
  • Permissionless issuance: if the issuing choice's controller is non-privileged or argument-derived, a holder can inflate issuance past the cap (cross-reference AUTHORIZATION_MODEL).

Show full SKILL.md (359 more words)Show less

4. Fee / Rate Formula Verification at Normal Values

4a. Concrete Example Computation

Pick 3 representative rate values and trace through the actual choice-body formula:

Fee ParamValueFormulaInput AmountExpected OutputActual OutputMatch?

Tag: [BOUNDARY:fee_bps={val} -> effective_rate={computed}]

Note: Decimal is fixed-point (10 fractional digits); verify the formula's scale matches the field's declared type.

Red flags:

  • Gross-up: amount * MAX / (MAX - fee) charges a higher effective rate than fee/MAX.
  • Fee-on-fee: one fee's output feeds another's input across chained choices — combined rate is not the sum.
  • Rounding direction: Decimal/Int division truncates toward zero — verify the intended direction and that it does not let the protocol keep dust on every operation.
  • Division order: amount * rate / MAX vs amount / MAX * rate — the second loses precision for small amounts.
4b. Fee-Base Consistency

For every fee computation, trace the base amount through ALL subsequent choice consequences:

Fee Site (Template.Choice)Base FieldReduced After Fee?HowFee Recomputed?Overcharge?

Methodology: identify the fee base field → trace FORWARD through the successor create → if the base is reduced (capped, adjusted) AFTER the fee is computed → fee charged on a larger base than processed.

4c. Fee Impact on Conservation

If a fee is taken during split/transfer: does child1.amount + child2.amount + fee == parent.amount? With Decimal truncation, does deposit-vs-withdraw rounding consistently favor one party? Cross-reference SHARE_ALLOCATION_FAIRNESS.


5. Emission / Inflation Sustainability

For protocols with emission/reward distribution via choices:

  • Maximum amount mintable per transaction / per ledger-time period?
  • Can cumulative emissions exceed a reward-pool contract's tracked balance (CONTRACT abort on transfer, or silent over-issuance if unchecked)?
  • Is there a supply-cap contract? Can a choice bypass it (Section 3)?
  • What happens when a reward-pool contract is exhausted — does the distribute choice abort (PreconditionFailed / NO_SUCH_KEY)?
Emission ParamMax per TxPool Balance RequiredTxns to Depletion at MaxCap Contract Exists?

Finding Template

markdown
**ID**: [DML-EDA-N]
**Verdict**: CONFIRMED / PARTIAL / REFUTED / CONTESTED
**Step Execution**: ✓1,2,3,4,5 | ✗(reasons) | ?(uncertain)
**Rules Applied**: [R2:___, R10:___, R13:___, R14:___]
**Severity**: Critical/High/Medium/Low/Info (Int/Decimal overflow is a LIVENESS finding, NOT auto-downgraded as silent-wrap)
**Location**: {Module}.daml:LineN (template X, choice Y)
**Title**: {parameter boundary / invariant break / cap-not-tracked / fee miscalculation}
**Description**: {specific issue with code reference and a numerical Decimal/Int example}
**Impact**: {quantified at worst-state operational parameters — Rule 10}
**PoC steer**: boundary-value Scripts (set field to 0 / max / negative and trace the consuming choice), or a multi-transaction Script that issues past a cap because the accumulator contract was not updated; assert conservation/cap violated, or the consuming choice aborts (liveness).

Step Execution Checklist (MANDATORY)

SectionRequiredCompleted?Notes
1. Parameter Boundary AnalysisYES
2. Economic Invariant IdentificationYES
3. Accumulator / Cap Coherence Across TransactionsYESR14 — primary DAML lane, never skip
4. Fee / Rate Formula VerificationIF fee/rate parameters detected
5. Emission / Inflation SustainabilityIF emission/reward detected

If any step skipped, document a valid reason (N/A, single parameter, no fees, no emissions, no cap).

© PlamenTSV, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in agents/skills/daml/economic-design-audit of PlamenTSV/plamen.

Open the folder on GitHubat commit 795962b

Compare with similar skills

Economic Design Audit 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.

Economic Design Audit compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Economic Design Audit this skillPlamenTSV/plamen303—~2.2kAutomated safety check: PassMIT
Consult ClaudeEpicenterHQ/epicenter4.8k—~2kAutomated safety check: PassCustom licence
System Atlasinkboard/system-atlas430—~2.3kAutomated safety check: PassMIT
Design Image Studiokangarooking/design-image-studio102—~1.5kAutomated safety check: PassMIT
Kicad Reviewmixelpixx/Konnect927—~3.2kAutomated safety check: PassAGPL-3.0
Design AuditUniClipboard/UniClipboard1.9k—~554Automated safety check: PassAGPL-3.0

Similar skills

  • Consult Claude

    EpicenterHQ/epicenter

    Assign Claude Code a read-only investigation, recommendation, or finished text draft.

    4.8k GitHub stars~2k tokensUpdated 2 days ago
    Media & CreativeAuto-check passed
  • System Atlas

    inkboard/system-atlas

    Build and maintain an explorable, progressively-disclosed isometric "atlas" of a system's architecture — an interactive page (hover to read, click to pin, go inside for steps, moving data packets…

    430 GitHub stars~2.3k tokensUpdated 1 mo ago
    Media & CreativeAuto-check passed
  • Design Image Studio

    kangarooking/design-image-studio

    Directly generate design-oriented AI images with strong creative direction and prompt engineering.

    102 GitHub stars~1.5k tokensUpdated 5 mo ago
    Media & CreativeAuto-check passed
  • Kicad Review

    mixelpixx/Konnect

    Design review and validation workflow for KiCAD projects via MCP tools.

    927 GitHub stars~3.2k tokensUpdated 5 days ago
    Media & CreativeAuto-check passed
  • Design Audit

    UniClipboard/UniClipboard

    定期审计代码库的工程设计问题(高心智复杂度、单一真相源被破坏、catch-all 胖接口、死代码、散落魔法字面量、泄漏抽象、资源生命周期靠环形缓冲)与可优化点,范围限定为自上次审计以来的 git churn,每条发现都落到 file:line 并对照本项目自己的 VISION.md / 各级 AGENTS.md / memory…

    1.9k GitHub stars~554 tokensUpdated today
    Media & CreativeAuto-check passed
  • L1 AI Design Review

    PaperMoonuu/Design-workflow-skills

    L1 × AI 设计评审:对已完成的单页、局部 UI 设计稿进行小型迭代评审,识别影响面、状态遗漏、文案与一致性风险,并给出 P0/P1/P2 建议和验收清单。用户提供 Figma 链接、截图、前后设计稿或可评审原型,并要求设计走查、风险评审或开发前 UI 检查时使用;不用于设计前方案预检、完整多页面流程或 L2 开发交付。

    316 GitHub stars~492 tokensUpdated 19 days ago
    Media & CreativeAuto-check passed

More from PlamenTSV/plamen

All 87 skills in this repo
  • Audit Prep

    PlamenTSV/plamen

    Prepare Solidity projects for a security audit — test coverage, test quality, NatSpec docs, code hygiene, dependency health, best-practice enforcement, deployment readiness, and project…

    303 GitHub stars~3.7k tokensUpdated 14 days ago
    Auto-check passed
  • Verification Protocol

    PlamenTSV/plamen

    Trigger Pattern Always (used by all verifier agents) - Inject Into security-verifier agents (Phase 5)

    303 GitHub stars~3.5k tokensUpdated 14 days ago
    Auto-check passed
  • Ability Analysis

    PlamenTSV/plamen

    Trigger Pattern Always (Aptos Move) - foundational security check - Inject Into Breadth agents, depth agents

    303 GitHub stars~3.3k tokensUpdated 14 days ago
    Auto-check passed
  • Ability Analysis

    PlamenTSV/plamen

    Trigger Pattern Always (Sui Move) -- foundational security check - Inject Into Breadth agents, depth agents

    303 GitHub stars~3.2k tokensUpdated 14 days ago
    Auto-check passed
  • Account Lifecycle

    PlamenTSV/plamen

    Trigger Pattern ACCOUNTCLOSING flag detected (close/CloseAccount usage) - Inject Into Breadth agents, depth agents

    303 GitHub stars~1.2k tokensUpdated 14 days ago
    Auto-check passed
  • Account Validation

    PlamenTSV/plamen

    Trigger Pattern Always required for Solana audits - Inject Into Breadth agents, depth agents

    303 GitHub stars~1.7k tokensUpdated 14 days ago
    Auto-check passed

Questions about Economic Design Audit

What does Economic Design Audit do?

Trigger Pattern MONETARYPARAMETER flag (fee, rate, emission, cap, bps as template fields) - Inject Into Breadth agents (merged via M4 hierarchy). Economic Design Audit is an agent skill from PlamenTSV/plamen.

When should I use Economic Design Audit?

Economic Design Audit fits situations like: pattern MONETARYPARAMETER flag (fee; bps as template fields) - Inject Into Breadth agents (merged via M4 hierarchy).

How do I install Economic Design Audit in Claude Code?

Run `npx skills add PlamenTSV/plamen --skill economic-design-audit -a claude-code`. Or copy the skill folder (agents/skills/daml/economic-design-audit in PlamenTSV/plamen) into .claude/skills/economic-design-audit in your project. Claude Code loads it when a task matches its description.

How do I install Economic Design Audit in Codex?

Run `npx skills add PlamenTSV/plamen --skill economic-design-audit -a codex`. Or copy the skill folder (agents/skills/daml/economic-design-audit in PlamenTSV/plamen) into .agents/skills/economic-design-audit in your project. Codex loads it when a task matches its description.

Can I use Economic Design Audit 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 PlamenTSV/plamen --skill economic-design-audit -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/economic-design-audit, .gemini/skills/economic-design-audit, .github/skills/economic-design-audit and .opencode/skills/economic-design-audit in your project.

What does Economic Design Audit need to run?

Going by SKILL.md and its folder, Economic Design Audit needs credentials named NO_SUCH_KEY. Our summary lists: A credential in NO_SUCH_KEY.

Does Economic Design Audit 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 Economic Design Audit 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 Economic Design Audit use?

Economic Design Audit is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Economic Design Audit use?

About 2.2k tokens (SKILL.md is roughly 8.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Economic Design Audit?

Skills that share tags, products or a category with Economic Design Audit: Consult Claude (EpicenterHQ/epicenter, 4.8k stars), System Atlas (inkboard/system-atlas, 430 stars), Design Image Studio (kangarooking/design-image-studio, 102 stars) and Kicad Review (mixelpixx/Konnect, 927 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Economic Design Audit?

PlamenTSV (a GitHub user) maintains it in PlamenTSV/plamen, which has 303 GitHub stars. The repository holds 87 skills in this directory. The repository was last updated on September 26, 2026.

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