Fortify Development
coollabsio/coolify
ACTIVATE when the user works on authentication in Laravel. An agent skill from coollabsio/coolify.
This skill should be used when making architectural decisions, writing specs, or reviewing decisions that contain "future work", "v2", "simpler for now", "out of scope", or complexity claims.
Install Decision Accountability
$ npx skills add jacob-dietle/context-os --skill decision-accountability -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install jacob-dietle/context-os decision-accountability --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/jacob-dietle/context-os.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/decision-accountability .claude/skills/decision-accountability && rm -rf skills-srcUse ~/.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/
Install the "decision-accountability" agent skill from https://github.com/jacob-dietle/context-os/tree/main/.claude/skills/decision-accountability into .claude/skills/decision-accountability/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "decision-accountability", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/jacob-dietle/context-os/tree/main/.claude/skills/decision-accountabilityType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add jacob-dietle/context-os --skill decision-accountability -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install jacob-dietle/context-os decision-accountability --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jacob-dietle/context-os.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/decision-accountability .agents/skills/decision-accountability && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "decision-accountability" agent skill from https://github.com/jacob-dietle/context-os/tree/main/.claude/skills/decision-accountability into .agents/skills/decision-accountability/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "decision-accountability", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add jacob-dietle/context-os --skill decision-accountability -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install jacob-dietle/context-os decision-accountability --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jacob-dietle/context-os.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/decision-accountability .cursor/skills/decision-accountability && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "decision-accountability" agent skill from https://github.com/jacob-dietle/context-os/tree/main/.claude/skills/decision-accountability into .cursor/skills/decision-accountability/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "decision-accountability", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/jacob-dietle/context-os.git --path .claude/skills/decision-accountability--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add jacob-dietle/context-os --skill decision-accountability -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install jacob-dietle/context-os decision-accountability --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jacob-dietle/context-os.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/decision-accountability .gemini/skills/decision-accountability && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "decision-accountability" agent skill from https://github.com/jacob-dietle/context-os/tree/main/.claude/skills/decision-accountability into .gemini/skills/decision-accountability/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "decision-accountability", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install jacob-dietle/context-os decision-accountabilityInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add jacob-dietle/context-os --skill decision-accountability -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/jacob-dietle/context-os.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/decision-accountability .github/skills/decision-accountability && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "decision-accountability" agent skill from https://github.com/jacob-dietle/context-os/tree/main/.claude/skills/decision-accountability into .github/skills/decision-accountability/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "decision-accountability", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add jacob-dietle/context-os --skill decision-accountability -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install jacob-dietle/context-os decision-accountability --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jacob-dietle/context-os.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/decision-accountability .opencode/skills/decision-accountability && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "decision-accountability" agent skill from https://github.com/jacob-dietle/context-os/tree/main/.claude/skills/decision-accountability into .opencode/skills/decision-accountability/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "decision-accountability", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
decision-accountability- GitHub stars
- 111
- Token cost
- ~1.9k tokens
- SKILL.md length
- 721 words
- Files
- 2 (incl. references)
- Skills in repo
- 11
- Repo updated
- First seen
- Licence
- MIT
At a glance
This skill should be used when making architectural decisions, writing specs, or reviewing decisions that contain "future work", "v2", "simpler for now", "out of scope", or complexity claims.
- Works in 5 steps: Extract Decisions and Claims → Verify Every Claim → Ownership Test → …
- Tasks that involve Authentication
- SKILL.md covers When to Use, The Dual Failure Mode, Step 1: Extract Decisions and… and Step 2: Verify Every Claim, plus 6 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Decision Accountability is an agent skill from jacob-dietle/context-os. This skill should be used when making architectural decisions, writing specs, or reviewing decisions that contain "future work", "v2", "simpler for now", "out of scope", or complexity claims. Verifies assumptions are grounded and catches corner-cutting disguised as pragmatism. Applies to code, specs, data models, auth flows, and context structures.
Its SKILL.md is about 1.9k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/failure-patterns.md`).
It sits in Backend & APIs, covering Authentication. The licence is MIT.
When your agent uses it
- Tasks that involve Authentication
Example prompts
- “future work”
- “simpler for now”
- “out of scope”
- “/decision-accountability”
Workflow steps
5 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit 1027e3f. 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 no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Decision Accountability loads about 1.9k tokens when it runs, and up to ~3.2k if it reads all its reference files. Until then it costs about 94 tokens; SKILL.md has 721 words of instructions outside code blocks.
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 jacob-dietle/context-os at commit 1027e3f, republished under its MIT licence (© jacob-dietle). 721 words, ~1,904 tokens.
Download SKILL.mdSave it as
.claude/skills/decision-accountability/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.- name
- decision-accountability
- description
- This skill should be used when making architectural decisions, writing specs, or reviewing decisions that contain "future work", "v2", "simpler for now", "out of scope", or complexity claims. Verifies assumptions are grounded and catches corner-cutting disguised as pragmatism. Applies to code, specs, data models, auth flows, and context structures.
Decision Accountability
Unified check for assumption verification AND ownership accountability. Both failures lead to the same outcome: decisions that cost 10x to fix later.
When to Use
- Writing or reviewing specs
- Any architectural decision (code, auth, data model, context structure)
- When these phrases appear: "future work", "v2", "later", "simpler for now", "out of scope"
- When deferring anything that might be foundational
- Before finalizing any decision that persists
The Dual Failure Mode
Epistemic failure: "I assumed X was complex without checking" Ownership failure: "I avoided checking because the answer might mean more work"
Both produce: deferred foundations, duplicate implementations, tech debt disguised as pragmatism.
The laziness cascade:
- See decision point
- One path looks like more work
- Don't verify (because verification might confirm it's the right path)
- Pick easy path
- Dress it up as "tradeoff" or "v1 scope"
- Abdicate: "future work"
Step 1: Extract Decisions and Claims
From the spec/decision, list all claims and deferrals:
| Decision | Rationale Claims | Deferrals |
|---|---|---|
| [What was decided] | [Claims used to justify] | [What was pushed to "later"] |
Example:
| Decision | Rationale Claims | Deferrals |
|---|---|---|
| MCP has own /login | "Cross-subdomain is complex" | "SSO is future work" |
Step 2: Verify Every Claim
For each claim, attempt to falsify it:
Complexity Claims
Write the implementation. If it's <20 lines, the claim is falsified.
Claim: "Cross-subdomain cookies add complexity"
Verification:
cookies.set('session', token, { domain: '.tastematter.dev' });
Verdict: FALSIFIED — one line, not complexSimplicity Claims
Show both options concretely:
Claim: "Separate login per service is simpler"
Option A (spec chose): MCP /login + Browser /login = 2 implementations
Option B (alternative): Browser /login only = 1 implementation
Verdict: FALSIFIED — "simpler" option is actually more complexDeferral Claims
Calculate cost now vs later:
Claim: "SSO is future work"
Cost now: Use parent domain cookie (1 line change)
Cost later: Migrate two auth flows, reconcile sessions, update both services, migration period
Verdict: FALSIFIED — deferral costs 10x moreStep 3: Ownership Test
For each decision, answer honestly:
The Avoidance Check
Did you avoid verifying because the answer might mean more work?
If yes → Go verify NOW. You're avoiding, not deciding.
The Timeline Test
| Timeframe | Question | If answer is concerning... |
|---|---|---|
| 6 months | Will this be debt or foundation? | It's the wrong decision |
| 12 months | Will someone undo this to build forward? | It's the wrong decision |
| 5 years | Thank yourself or curse yourself? | It's the wrong decision |
The Maintenance Test
If you had to maintain this for 5 years, would you make the same decision?
If no → You're optimizing for "not my problem" — that's abdication, not engineering.
Step 4: Classify Deferrals
| Item | Foundational? | Can Defer? |
|---|---|---|
| Auth flow unification | YES | NO |
| Cookie/token scoping | YES | NO |
| Data models crossing boundaries | YES | NO |
| State multiple services share | YES | NO |
| API contracts between services | YES | NO |
| Spec architecture for multi-phase work | YES | NO |
| Additional OAuth provider | NO | YES |
| UI polish | NO | YES |
| Analytics | NO | YES |
| Documentation | NO | YES |
Foundational items cannot be deferred. There is no "v2" for foundations — only rewrites.
Step 5: Block or Proceed
If any foundational claim is falsified or deferred:
BLOCKED. Do not proceed. Revise decision first.
Provide:
- Which claims were falsified with evidence
- The actual implementation that disproves the complexity claim
- Revised decision based on verified assumptions
Show full SKILL.md (274 more words)Show less
If proceeding with legitimate deferrals:
Each deferral MUST have:
| Field | Required Content |
|---|---|
| Why not now | Actual blocker (not "too much work") |
| Cost comparison | Now vs later, with estimates |
| Owner | Who will do it (default: you) |
| Trigger/deadline | When it gets done |
No orphaned "future work." If you can't fill these out, you're abandoning, not deferring.
Output Format
## Decision Accountability Report
**Decision under review:** [What's being decided]
### Claims Verified
| Claim | Type | Verdict | Evidence |
|-------|------|---------|----------|
| "X is complex" | Complexity | VERIFIED/FALSIFIED | [Implementation or docs] |
| "Y is simpler" | Simplicity | VERIFIED/FALSIFIED | [Both options shown] |
| "Z can wait" | Deferral | VERIFIED/FALSIFIED | [Cost comparison] |
### Ownership Check
| Question | Answer | Concern? |
|----------|--------|----------|
| Avoided verification? | Yes/No | |
| 6mo: debt or foundation? | | |
| 12mo: undo to build forward? | | |
| 5yr: thank or curse? | | |
### Deferrals (if any)
| Item | Foundational? | Why not now | Cost now/later | Owner | Deadline |
|------|--------------|-------------|----------------|-------|----------|
| | | | | | |
### Verdict
[ ] **PROCEED** — all claims verified, no foundational deferrals
[ ] **BLOCKED** — falsified claims or foundational deferrals, revise first
### Revised Decision (if blocked)
[New decision based on verified assumptions and owned outcomes]Quick Reference
Red Flag Phrases
| Phrase | Action |
|---|---|
| "adds complexity" | Verify — write the implementation |
| "simpler for now" | Show total cost comparison |
| "future work" / "v2" | Foundational or additive? |
| "we can unify later" | At what cost? Show the math |
| "accepted tradeoff" | Is the analysis actually correct? |
| "out of scope" | Is this actually out of scope or foundational? |
Cannot Defer (Foundational)
- Auth / sessions / identity
- Data models crossing service boundaries
- Cookie / token scoping
- API contracts between services
- State that multiple services touch
- Spec architecture for complex multi-phase work
The Core Test
Would I make this decision if I'm maintaining it for 5 years?
If no, it's corner-cutting disguised as pragmatism. Do it right.
Evidence Base
Origin: C1 MCP Auth Foundation spec review (2026-04-23)
The spec contained decision D5:
"Login UI served from MCP worker directly (not browser worker)... Cross-subdomain cookie sharing adds complexity... Two login pages accepted for v1. Single-sign-on is future work."
Analysis revealed:
- "Cross-subdomain cookies" = one line:
domain: '.tastematter.dev' - "Two login pages simpler" = false, it's 2x implementation and maintenance
- "SSO is future work" = will cost 10x to unify later
Root causes identified:
- Epistemic: Complexity claim unverified
- Ownership: Avoided verification because answer meant more work
Pattern extracted: Both failures stem from optimizing for "less work now" at the cost of "much more work later" — and dressing it up as pragmatism.
© jacob-dietle, MIT. 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 1 other file (references) in .claude/skills/decision-accountability of jacob-dietle/context-os.
- SKILL.md
- references/failure-patterns.md
Open the folder on GitHubat commit 1027e3f
Compare with similar skills
Decision Accountability 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Decision Accountability this skilljacob-dietle/context-os | 111 | — | ~1.9k | Automated safety check: Pass | MIT | |
| Fortify Developmentcoollabsio/coolify | 63k | 4 repos | ~1.9k | Automated safety check: Pass | MIT | |
| Supabase Development and Debuggingsupabase/agent-skills | 2.7k | 3 repos | ~3.6k | Automated safety check: Pass | MIT | |
| Better Auth Best Practiceslatitude-dev/latitude-llm | 4.7k | 7 repos | ~1.6k | Automated safety check: Pass | MIT | |
| Gitnexus Exploringaws-samples/sample-kolya-br-proxy | 106 | 12 repos | ~749 | Automated safety check: Pass | MIT-0 | |
| Supabasecurvenote/curvenote | 170 | 5 repos | ~2.2k | Automated safety check: Pass | Custom licence |
Similar skills
- Official
Supabase Development and Debugging
supabase/agent-skills
General Supabase skill for database, auth, Edge Functions, Realtime and storage work, plus client libraries, migrations, security audits, debugging and reading logs.
Better Auth Best Practices
latitude-dev/latitude-llm
Configure Better Auth server and client, set up database adapters, manage sessions, add plugins, and handle environment variables.
- Official
Gitnexus Exploring
aws-samples/sample-kolya-br-proxy
A skill your agent uses when the user asks how code works, wants to understand architecture, trace execution flows, or explore unfamiliar parts of the codebase.
Supabase
curvenote/curvenote
A skill your agent uses when doing ANY task involving Supabase.
- Official
Gemini Live API Dev
google-gemini/gemini-skills
A skill your agent uses when building real-time, bidirectional streaming applications with the Gemini Live API, or migrating legacy Live models (2.0/2.5/3.1) to Gemini 3.8 Live.
More from jacob-dietle/context-os
All 11 skills in this repoBottleneck Attack
jacob-dietle/context-os
A skill your agent uses when deciding what to work on next, when progress is stuck, or when the reflex is to build or automate before proving the current bottleneck.
Code Service Defrag
jacob-dietle/context-os
This skill should be used to periodically defragment a multi-app/multi-service codebase — both CODE (duplicate deploy targets, colliding bindings, stale forks) and CONTEXT (parallel spec…
Content Strategy And Assembly
jacob-dietle/context-os
This skill should be used when producing content (newsletter posts, blog posts, LinkedIn posts) from existing corpus material.
Context Os CLI
jacob-dietle/context-os
This skill should be used when users ask about their work context, what they're working on, recent activity, file relationships, or knowledge graph structure.
Coordinated Agent Teams
jacob-dietle/context-os
This skill should be used when decomposing a spec into a multi-agent implementation plan with dependency ordering, parallelism decisions, contract testing, and verification strategy.
Eval Loop
jacob-dietle/context-os
This skill should be used when a specific quality problem (UX, data, architecture, feature) needs systematic diagnosis and iterative fixing toward a defined target.
Related
Categories
Questions about Decision Accountability
What does Decision Accountability do?
This skill should be used when making architectural decisions, writing specs, or reviewing decisions that contain "future work", "v2", "simpler for now", "out of scope", or complexity claims. Decision Accountability is an agent skill from jacob-dietle/context-os. This skill should be used when making architectural decisions, writing specs, or reviewing decisions that contain "future work", "v2", "simpler for now", "out of scope", or complexity claims.
When should I use Decision Accountability?
Decision Accountability fits situations like: tasks that involve Authentication.
How do I install Decision Accountability in Claude Code?
Run `npx skills add jacob-dietle/context-os --skill decision-accountability -a claude-code`. Or copy the skill folder (.claude/skills/decision-accountability in jacob-dietle/context-os) into .claude/skills/decision-accountability in your project. Claude Code loads it when a task matches its description.
How do I install Decision Accountability in Codex?
Run `npx skills add jacob-dietle/context-os --skill decision-accountability -a codex`. Or copy the skill folder (.claude/skills/decision-accountability in jacob-dietle/context-os) into .agents/skills/decision-accountability in your project. Codex loads it when a task matches its description.
Can I use Decision Accountability 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 jacob-dietle/context-os --skill decision-accountability -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/decision-accountability, .gemini/skills/decision-accountability, .github/skills/decision-accountability and .opencode/skills/decision-accountability in your project.
What does Decision Accountability need to run?
SKILL.md names no scripts, command-line tools or credentials: Decision Accountability is instructions for the agent only.
Does Decision Accountability 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 Decision Accountability 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 Decision Accountability use?
Decision Accountability 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 Decision Accountability use?
About 1.9k tokens (SKILL.md is roughly 7.6k 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 1.3k tokens, read only when the agent opens those files.
What are the alternatives to Decision Accountability?
Skills that share tags, products or a category with Decision Accountability: Fortify Development (coollabsio/coolify, 63k stars), Supabase Development and Debugging (supabase/agent-skills, 2.7k stars), Better Auth Best Practices (latitude-dev/latitude-llm, 4.7k stars) and Gitnexus Exploring (aws-samples/sample-kolya-br-proxy, 106 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Decision Accountability?
jacob-dietle (a GitHub user) maintains it in jacob-dietle/context-os, which has 111 GitHub stars. The repository holds 11 skills in this directory. The repository was last updated on August 13, 2026.
Source: jacob-dietle/context-os on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.