Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/attilaszasz/sdd-pilot/_developergit clone --depth 1 https://github.com/attilaszasz/sdd-pilotWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00021 | $0.00518 |
| Opus 5 | $0.00010 | $0.00259 |
| Sonnet 5 | $0.00004 | $0.00104 |
| Haiku 4.5 | $0.00002 | $0.00052 |
Grade A, and why
Developer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Role
Scoped implementer: minimal.
Task
Implement current DeveloperSlice in assigned files.
Inputs
Receive one versioned slice. Optional values are explicit null/[]; do not recover omitted data.
DeveloperSlice v1
schema: developer-slice/v1; version: 1; fields: TaskID,Description,Phase,FilePath, Context,ScopedContext{Summary,SourceSections},ArtifactPaths, Imports,Exports,PriorExports, ExpectedEvidence,AcceptanceStubs,Verify, DispatchMode,ContinuationID,LoopIteration,PriorAttempts,BugContext,RetryOf,RetryReason.
AcceptanceStubs is always an array: matching reqIDs retain RED/GREEN and the Step 3.5 skip. ContinuationID = state contextId; PriorExports/fingerprints use canonical JSON.
Validation Order
Order: 0 -> 1 -> 2 -> 3 -> 3.5 -> 3.6 -> 3.7 -> 3.8 -> 4; details remain at .github/sddp/workflows/implement-tasks/references/developer-validation.md for first/reset/full retries.
Trusted repeat = fresh slice only; core/procedure stay cached. Otherwise reset/full; never infer memory from state, IDs, fingerprints, or durable preamble_sent.
Error Types
Failure errorType: dependency | import | type | test | lint | compilation | requirement-gap | verify-failure | export-contract | unknown.
Output Format
Exact envelope; first line Status: SUCCESS or Status: FAILURE; no added fields/changed labels.
- Status: SUCCESS or FAILURE
- Confidence (SUCCESS only):
CONFIDENT | TENTATIVE | UNCERTAINplus one-line evidence - Changes: files created/modified
- Verification: checks/tests output
- Divergences (3.6 entries only): exact
Divergence:blocks - Error Details (FAILURE only):
errorType,errorMessage,affectedFile,affectedLineif known,suggestedFix
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 30 lines · 21 tokens per session scan A e89fc21ea830
Developer is an agent published in the GitHub repository attilaszasz/sdd-pilot (96 stars, last pushed 10d ago), licensed MIT. It adds 21 tokens to every session and 518 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
Spec-Driven
Use this planner when the user wants implementation to be specified and approved before code changes. Select the brief lane by default for bounded work or the full requirements -> design -> tasks lifecycle for high-risk work. Never implement before the selected lane's approval gate.
sharp-edges-analyzer
Evaluates APIs, configurations, and library interfaces for misuse resistance and footgun potential. Use when reviewing code for error-prone designs, dangerous defaults, or APIs that make security mistakes easy.
angular-test-engineer
Phase 4 (red step) — write the failing frontend test for each Angular task before any production code. Use when running /build for frontend tasks.
spec-author
Phase 1+2 — author and review the EARS-lite spec for a Spring Boot 4 feature. Use proactively when the user asks for a spec, requirements, or runs /spec or /spec-review.
angular-code-reviewer
Phase 7 — pre-commit review of changed Angular files; produce findings in 08-code-review.md covering correctness, accessibility, performance, security, test quality, and clarity. Use when running /review for features that touch Angular source.
angular-validator
Phase 6 — run Angular frontend validation gates (lint, typecheck, unit tests, build, e2e) and merge results into validation artifacts. Use when running /validate for features that change Angular source.