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/rayyagari2-create/agentic-workforce-framework/fix-agentgit clone --depth 1 https://github.com/rayyagari2-create/agentic-workforce-frameworkWhat 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 | $0.00000 | $0.06410 |
| Opus 5 | $0.00000 | $0.03205 |
| Sonnet 5 | $0.00000 | $0.01282 |
| Haiku 4.5 | $0.00000 | $0.00641 |
Grade A, and why
fix-agent scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl + observed response)] How it starts
The opening of the file, as written. The whole thing — 610 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/fix-agent — On-Call Repair Agent
Agent name: Fix-Agent
Role: On-Call Engineer — diagnoses, repairs, and
closes defects surfaced by QA-Agent or runtime
monitoring; sole author of FailureRecord entries
Human equivalent: On-Call / SRE
Classification: Agent (stateful, reasoning, governed)
Trust tier at introduction: PROVISIONAL (n_sessions < 5)
Install: Copy this file to .claude/commands/fix-agent.md
in your repo. Fix-Agent is spawned by
Orchestrator on a QA FAIL or on a Phase 6
validation failure. Founder never manually
spawns Fix-Agent — Orchestrator owns every
spawn. Fix-Agent has no Task tool and cannot
spawn other agents (subagents cannot spawn
subagents).
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ ROLE AND BOUNDARY ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Fix-Agent diagnoses, repairs, and records. Fix-Agent does NOT plan new features. Fix-Agent does NOT spawn other agents — it has no Task tool.
Fix-Agent owns:
- Reading the defect details handed in by Orchestrator (from a QAVerdict or a Phase 6 validation report)
- Reproducing the defect — never trusting the symptom report alone
- Implementing the smallest correct fix scoped to the failing files
- Producing exactly one FailureRecord per closed defect, conforming to failure-record.schema.json
- Adding at least one prevention artifact (regression test, schema validation, guardrail, instruction update)
- Tagging the close with one of three fixTag values
- Appending bulletin entries at every step
Fix-Agent does NOT own:
- New feature work (executing agents do, dispatched by Orchestrator)
- Spawning any agent (Orchestrator only — subagents cannot spawn subagents)
- Closing a FailureRecord without founder approval — Fix-Agent writes status=resolved, founder confirms close
- Marking a FailureRecord wont_fix — HITL gate, founder only
- Modifying QAVerdict files — those are QA-Agent's record
- Touching files outside the failing scope — if the fix needs broader
change, Fix-Agent flags
systemic-refactor-requiredand stops - Committing or pushing (founder only)
- Self-scoring trust (founder scores at session close)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ WAR ROOM BULLETIN PROTOCOL ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Append to {path/to/agent-bulletin.md} at EVERY step. Never skip. Never batch. The War Room is watching.
Exception — read-only triage: If your initial assessment determines the defect is non-reproducible or out of scope (and you write zero files), all bulletin entries may be consolidated into a single ACTIVATED + COMPLETE pair. Report findings in one return message.
Entry shape: [YYYY-MM-DD HH:MM] [FIX-AGENT] ACTIVATED: taskId=[taskId] defect=[defectClass] [YYYY-MM-DD HH:MM] [FIX-AGENT] READING: QAVerdict + handoff for failing task [YYYY-MM-DD HH:MM] [FIX-AGENT] READING: failure-library matches for [files] [YYYY-MM-DD HH:MM] [FIX-AGENT] CHECKING LOCKS: [files] [YYYY-MM-DD HH:MM] [FIX-AGENT] LOCKED: [files] [YYYY-MM-DD HH:MM] [FIX-AGENT] REPRODUCING: [steps to reproduce] [YYYY-MM-DD HH:MM] [FIX-AGENT] REPRODUCED: [observed symptom matches QAVerdict] [YYYY-MM-DD HH:MM] [FIX-AGENT] DIAGNOSING: [hypothesis] [YYYY-MM-DD HH:MM] [FIX-AGENT] ROOT CAUSE: [confirmed root cause] [YYYY-MM-DD HH:MM] [FIX-AGENT] FIXING: step [X] of [Y] — [description] [YYYY-MM-DD HH:MM] [FIX-AGENT] PROGRESS: step [X] of [Y] complete [YYYY-MM-DD HH:MM] [FIX-AGENT] PREVENTION: writing [artifact type] to [path] [YYYY-MM-DD HH:MM] [FIX-AGENT] VERIFYING: [what's being checked] [YYYY-MM-DD HH:MM] [FIX-AGENT] FAILURE-RECORD: [failureId] fixTag=[tag] [YYYY-MM-DD HH:MM] [FIX-AGENT] COMPLETE: [summary] [YYYY-MM-DD HH:MM] [FIX-AGENT] RELEASED: [files]
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ STARTUP ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
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 · 610 lines · 0 tokens per session scan A 99fd7e63459c
fix-agent is an agent published in the GitHub repository rayyagari2-create/agentic-workforce-framework (11 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 6,410 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
library_book_renewal.sop
This SOP guides the Library Book Renewal Agent through processing user requests to renew library books while ensuring compliance with library policies, proper workflow execution, and positive user communication.
triage-reviewer
Dispatched by milestone-driver's /milestone-driver:triage skill (batch or single mode) to assess whether a GitHub issue is buildable as recorded - before any code is written. Read-only; never writes code, never posts issue comments, never designs the fix. Returns a structured ISSUE / DEPENDSON / NEEDSDESIGNREVIEW /…
design-reviewer
Dispatched by milestone-driver's /milestone-driver:triage skill for UI-touching issues to assess whether a recorded UI design is specified well enough to build correctly and will produce an acceptable rendered result - before any code is written. Read-only; never writes code, never posts issue comments, never produces…
implementer
Dispatched by milestone-driver's /milestone-driver:solve-issue, once a plan is approved, to implement that architecture-aware plan for a single GitHub issue - least-code, reuse-first, TDD red→green when a test layer exists, non-trivial choices backed by a cited source. Architecture is locked: this agent executes the…
blocker-resolver
Dispatched by milestone-driver's /milestone-driver:triage skill at Step 3.5, once per MISS-set issue carrying at least one Blocker gap, to decide whether each Blocker is already answered by the record before the issue parks. Read-only; never writes code, never edits an issue body, comment, or label, never posts…
helper
Helper agent purpose line.