AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Effort Modeling

skill-flatbreadlabs-flatbread-effort-modeling · by FlatbreadLabs

Sharpen a project's vocabulary and planning through one-question-at-a-time grilling, then journal Decisions, Constraints, Findings, Issues, and Risks into the Flatbread Proof. Use when a plan needs durable reasoning instead of ADRs.

No reviews yet
0 installs
16 views
0.0% view→install

Install

$ agentstack add skill-flatbreadlabs-flatbread-effort-modeling

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-flatbreadlabs-flatbread-effort-modeling)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
21d ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Effort Modeling? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Effort modeling

Use this discipline while a plan or design is being shaped. Store planning records in the Proof. Keep project terms in a glossary such as CONTEXT.md or docs/glossary.md.

Resume before asking

From the project root, use the proof skill's bounded reads:

  1. flatbread proof list --status active
  2. For the relevant Effort, inspect open Issues and blocking Decisions.
  3. Read a record or digest when a prior conclusion affects the question.

Look up facts in code instead of asking. Put decisions to the user; do not answer them autonomously.

During the grill

Ask one question at a time. Offer a recommendation, wait for the user's answer, and resolve prerequisite choices before dependent ones.

  • Challenge a term that conflicts with the glossary.
  • Sharpen vague or overloaded terms.
  • Use concrete edge cases to test relationships and scope.
  • Compare a claim about behavior with the code and surface contradictions.
  • Update the relevant project glossary when vocabulary resolves. Keep it free

of implementation details and planning rationale.

Journal the right speech act

Use flatbread proof write for the current Effort, following [the Proof reference](../proof/reference.md):

  • Finding — evidence about code, users, or runtime behavior.
  • Issue — a question, defect, gap, or blocker needing attention.
  • Constraint — a sticky hard or soft boundary.
  • Risk — a prospective negative outcome with likelihood and severity.
  • Decision — a proposed or accepted commitment among alternatives.

Two kinds of links

Use these links for different purposes:

  • cites — links a record to a Citation for an external URL,

document, or saved source. Records never cite Blobs directly.

  • derives_from — links a record to the Findings, Constraints, Risks,

and Issues that informed it.

A Decision typically uses derives_from for project reasoning and cites for outside sources.

External evidence (URL or longform)

When a Finding, Issue, Decision, Constraint, or Risk rests on an external source, create a Citation instead of copying the source into the record body:

  1. WriteBlob — only when you need to save large or non-text content

(markdown, JSON, an image, and so on).

  1. WriteCitation — body is often the URL string; pass optional blob and

role when needed.

  1. Create the record — pass cites: [""] when creating the

Finding, Issue, Decision, Constraint, or Risk. You cannot add a citation later, so create the Citation first.

Record a Decision when it is hard to reverse, surprising without context, and the result of a real trade-off. Create it as proposed while the user is still deciding; call AcceptDecision only after they commit. Always pass "rejectSiblings": false unless deliberately closing every competing proposal.

Use the long-form body template in [DECISION-BODY.md](./DECISION-BODY.md) when the rationale would otherwise be lost. The body is the durable explanation; do not create an ADR alongside it.

Finish

Capture accepted Decisions, unresolved Issues, and material Findings before ending the session. For an immediate verification read, use the generation returned by the mutation with --strict-min-generation.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.