fire-reflect

fire-reflect is a command for coding agents from ThierryN/fire-flow. It costs 3 tokens per session (1,585 once invoked), scanned A, original, MIT.

A command for recording and finding notes about failures during debugging, testing, or stalled work. Each reflection records what was tried, why it failed, and what eventually worked.

In plain words
What is it for?
Use it to capture a resolved failure, search past notes by symptom, list stored reflections, or review them by project or severity.
Why use it?
It prevents the same investigation from being repeated in later sessions. Searching earlier reflections can provide clues about recurring errors or approaches.

Command

Part of the dominion-flow plugin — 44 commands, 15 agents shipped together

Install

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.

agentmods
npx agentmods add commands/thierryn/fire-flow/fire-reflect
Clone the repo
git clone --depth 1 https://github.com/ThierryN/fire-flow

Or install dominion-flow, the plugin that ships this one along with the rest of its 44 commands, 15 agents.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for fire-reflect

README.md
[![agentmods](https://agentmods.dev/badge/commands/thierryn/fire-flow/fire-reflect.svg)](https://agentmods.dev/commands/thierryn/fire-flow/fire-reflect)
Your own site
<a href="https://agentmods.dev/commands/thierryn/fire-flow/fire-reflect"><img src="https://agentmods.dev/badge/commands/thierryn/fire-flow/fire-reflect.svg" alt="Measured on agentmods" height="20"></a>
Per session 3 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,585 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What 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.

ModelPer sessionOnce invoked
Fable 5 $0.00003 $0.01585
Opus 5 $0.00002 $0.00792
Sonnet 5 $0.00001 $0.00317
Haiku 4.5 $0.00000 $0.00159

Measured 4d ago against content hash 21959c0494d0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

fire-reflect 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 4d 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.

commands/fire-reflect.md · 238 lines

How it starts

The opening of the file, as written. The whole thing — 238 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/fire-reflect

Capture, search, and review failure reflections. Reflexion-style self-reflection for cross-session learning.


Purpose

After any failure (debug resolution, test failure, approach rotation, stalled loop), capture what was tried, why it failed, and what actually worked as a persistent reflection. Future sessions search these before investigating.


Arguments

arguments:
  action:
    required: false
    type: string
    description: "Action to perform: capture (default), search, list, review"
    example: "/fire-reflect capture"

optional_flags:
  --from debug: "Auto-extract from most recent resolved debug session"
  --from session: "Extract from current session context"
  --project <name>: "Tag with project name"
  --severity <level>: "minor | moderate | critical (default: moderate)"
  --search <query>: "Search reflections by keyword/symptom"

Process

Step 1: Determine Action

IF args contain "search" or --search:
  → Go to Search Mode (Step 5)
IF args contain "list":
  → Go to List Mode (Step 6)
IF args contain "review":
  → Go to Review Mode (Step 7)
ELSE:
  → Capture Mode (Step 2)

Step 2: Gather Reflection Content

If --from debug:

  • Read most recent file in .planning/debug/resolved/
  • Extract: symptoms, eliminated hypotheses, root cause, fix applied
  • Auto-fill reflection fields

If --from session:

  • Review current conversation context
  • Identify: failed approaches, what was tried, what worked
  • Auto-fill reflection fields

If interactive (default): Ask using AskUserQuestion:

  1. What was the problem? — Brief symptom description
  2. What did you try that failed? — Each approach and why it didn't work
  3. What actually worked? — The solution that resolved it
  4. The lesson — One-sentence takeaway for future self
  5. Search triggers — When should future agents find this?

Step 3: Generate Reflection File

Create file at ~/.claude/reflections/{date}_{slug}.md:

Read the full file on GitHub · 238 lines

Changes

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.

  1. 4d ago First seen · 238 lines · 3 tokens per session scan A 21959c0494d0

Subscribe to this mod's changes

fire-reflect is a command published in the GitHub repository ThierryN/fire-flow (77 stars, last pushed 21d ago), licensed MIT. It adds 3 tokens to every session and 1,585 once invoked, about $0.0000 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.