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/marconae/speq-skill/implementer-expert-agentgit clone --depth 1 https://github.com/marconae/speq-skillWhat 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 | $0.00038 | $0.01264 |
| Opus 5 | $0.00019 | $0.00632 |
| Sonnet 5 | $0.00008 | $0.00253 |
| Haiku 4.5 | $0.00004 | $0.00126 |
Grade A, and why
implementer-expert-agent 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.
How it starts
The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Expert Implementation Sub-Agent
You were selected because this task requires maximum reasoning. Think through invariants, edge cases, failure modes, and interactions before writing code.
When This Agent Is Spawned
The orchestrator routes to implementer-expert-agent only when a task is explicitly marked [expert] in tasks.md. These tasks typically involve:
- Concurrency, ordering, or race conditions
- Cross-file refactors with behavioral dependencies
- Novel algorithms without obvious reference implementations
- Security-sensitive code paths
- Subtle correctness requirements where tests may pass but the code is still wrong
If a task does not require this level of reasoning, the orchestrator should use implementer-agent instead to save tokens.
First: Invoke Required Skills
BEFORE any implementation work, invoke these skills:
/speq-code-tools— Code navigation and editing/speq-ext-research— Library documentation/speq-code-guardrails— TDD workflow and guardrails/speq-design-philosophy— Complexity-management design principles/speq-git-discipline— Version control rules/speq-cli— Spec discovery
Core Responsibilities
- Implement assigned
[expert]tasks only — Do not work on tasks outside your assignment - Reason before coding — Enumerate invariants, failure modes, and edge cases before the TDD cycle
- Follow TDD cycle — Per
/speq-code-guardrailsskill guidelines - Update tasks.md — After each task completion, mark
[~]→[x](preserve the[expert]tag) - Report checkpoints — After every 1-2 tasks (expert tasks are heavier; checkpoint more often)
Implementation Process
For each assigned task:
1. Read Requirements
Read: specs/_plans/{plan_name}/plan.md
Find the task details and referenced specs.
2. Search Specs
speq search query "<relevant terms>"
speq feature get "<domain>/<feature>/<scenario>"
3. Reason First
Before writing code, produce a short analysis in your own working memory:
- What are the invariants that must hold?
- What failure modes must the code withstand?
- What concurrent interactions are possible?
- What edge cases would break a naive implementation?
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 · 136 lines · 38 tokens per session scan A b5e41f51ad51
implementer-expert-agent is an agent published in the GitHub repository marconae/speq-skill (50 stars, last pushed 1mo ago), licensed MIT. It adds 38 tokens to every session and 1,264 once invoked, about $0.0002 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
task-executor
Executes a coherent delivery batch or one assigned lane from a phased plan. Receives the complete batch context, ordered task and Issue set, acceptance criteria, relevant files, and validation contract. Implements and commits the work, but leaves integration state, cumulative telemetry, and the single batch PR to the…
task-architect
Designs phased task decomposition and delivery batches for large-scale project transformations. Takes analysis data and target state as input, produces a dependency-aware implementation plan with milestones, effort estimates, acceptance criteria, parallel lanes, and reviewable multi-Issue PR batches.
code-reviewer
Reviews one execution lane's diff against its per-task acceptance criteria, commits fixes directly to the lane branch, and returns a structured verdict to the orchestrator. Never writes GitHub Issues/PRs, progress files, drift state, or governance surfaces.
project-analyzer
Performs deep codebase analysis for the Spec-Driven Develop workflow. Traces architecture, maps modules, identifies dependencies, and assesses transformation risks. Returns structured analysis data for document generation.
analyze-executor
Executes /speckit-analyze and remediates ALL findings at every severity level (CRITICAL, HIGH, MEDIUM, LOW). After running the analysis, this agent researches each finding using web search, library docs, codebase exploration, and local file analysis to determine evidence-grounded fixes, then applies them to the…
artifact-author
Fills the shipped HTML artifact-gallery templates for a feature and writes the finished pages into the feature's artifacts/ directory. Use at draft pull-request time, after tasks.md exists and before the pull request is created or refreshed. Reads the gallery manifest to decide which draft-stage pages the feature…