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 skills/asysta-act/agent-flow/implement-featurenpx skills add asysta-act/agent-flow --skill implement-featuregit clone --depth 1 https://github.com/asysta-act/agent-flowWhat 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 | $0.00023 | $0.02720 |
| Opus 5 | $0.00012 | $0.01360 |
| Sonnet 5 | $0.00005 | $0.00544 |
| Haiku 4.5 | $0.00002 | $0.00272 |
Grade A, and why
implement-feature 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 — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/implement-feature
Read and apply the mandatory execution guard defined in skills/implement-feature/data/guard-block.md BEFORE any other instruction in this file.
<stage_allowlist> required: code_analysis, fixer_reviewer, test, publisher optional: smoke_check, acceptance_gate </stage_allowlist>
You are a THIN CONTROLLER. Implement feature $ARGUMENTS from the issue tracker by dispatching specialist subagents via the Task tool. NEVER inline agent logic. Read ## Automation Config from CLAUDE.md.
Mode flag parsing
GOT_YOLO=false ; GOT_STEP_MODE=false
[[ "$ARGUMENTS" == *"--yolo"* ]] && GOT_YOLO=true
[[ "$ARGUMENTS" == *"--step-mode"* ]] && GOT_STEP_MODE=true
$GOT_YOLO && $GOT_STEP_MODE && { echo "[ERROR] Flags --yolo and --step-mode are mutually exclusive" >&2; exit 1; }
Additional flags parsed from $ARGUMENTS:
--decompose→decompose_mode = FORCE;--no-decompose→DISABLED; neither →AUTO--decompose-only→decompose_only_mode = true(implies FORCE; mutually exclusive with--no-decompose)--description "<text>"→description_mode = true; mutually exclusive with Issue ID--dry-run→ execute steps 01-02 only, display report, no side effects--clarification "<text>"→CLARIFICATION_TEXT = "<text>"; passed to../../core/resume-detection.md
Mode semantics: default = supervised autopilot (pauses only on NEEDS_CLARIFICATION); --yolo = zero gates to PR; --step-mode = pause after each step (c continue / s skip / a abort).
Configuration
Follow ../../core/config-reader.md. Required sections: Issue Tracker (Type, State transitions, On start set), Feature Workflow (Feature query, On start set), Source Control (Remote, Base branch, Branch naming), PR Rules (Labels), PR Description Template, Build & Test (Build, Test, Verify commands), Retry Limits, Module Docs, Hooks, Custom Agents, Notifications, Decomposition, Error Handling, Agent Overrides, Local Deployment, Pipeline Profiles. Full key list in docs/reference/automation-config.md.
What ships with it
9 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 147 lines · 23 tokens per session scan A 1164750e45d6
implement-feature is a skill published in the GitHub repository asysta-act/agent-flow (12 stars, last pushed 1mo ago), licensed MIT. It adds 23 tokens to every session and 2,720 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 skills, from other repositories
docs-planner
Identify documentation gaps and prioritize the docs backlog. Use when planning a docs improvement sprint, after signals surface repeated friction, when new SDK features ship without docs, or for periodic health assessment. Also triggers on "plan docs work", "what docs need writing", "prioritize the backlog", "docs…
azure-ai-projects-java
Azure AI Projects SDK for Java. High-level SDK for Azure AI Foundry project management including connections, datasets, indexes, and evaluations. Triggers: "AIProjectClient java", "azure ai projects java", "Foundry project java", "ConnectionsClient", "DatasetsClient", "IndexesClient".
goal-conductor
Own a long-horizon goal end to end - decompose it into work items, stand up one top-level session per item, patrol their state on a nudge loop, and decide each next round until the goal is met or a stop condition fires. Use when the user hands over a goal too large for one session ("clear the flaky-test backlog"…
goal-loop
Bootstrap a goal-driven self-improving AutoNudge loop. Give it a goal + anchor directory; it generates LOOP.md + GOAL.md + kanban board, then you write the Definition of Done and arm the loop. The running agent manages the board autonomously: finds issues, adds cards, resolves them, handoffs to Review, repeats until…
idea-forge
Three-mode idea engine - generate collides the week's zeitgeist with what you can ship into scored wedges; validate viability-screens the idea backlog; memo writes evidence-backed startup memos.
03_task5
Triages a support inbox, prioritizes urgent issues, routes each to the right internal team member, and drafts any customer-facing replies for review. Use when: catching up on a backlog of support messages, producing an escalation report, or routing issues to appropriate owners.