Catalog of Agent Neutralization Techniques

Just this once.

The one-time exception. The universal solvent.

Counter: The phrase itself is the red flag. If this time is genuinely different, that reasoning belongs in the rule.

"Too simple to test." "The process is overkill for something this small."

The rule doesn't apply because the task is small.

Counter: The process is fast for simple cases, so the waiver saves nothing and costs the habit.

I'll write the tests after.

The rule accepted in principle, postponed in practice, which is refusal with better manners.

Counter: The order is the discipline. After is a different (worse) activity with the same name.

I just need to explore first.

Rules start later; later never comes, and the exploration quietly becomes the implementation.

Counter: Explore freely, then throw the exploration away and start properly.

"Should work now." "I'm confident that's fixed."

Success declared from confidence instead of evidence. Banned words: should, probably, seems to.

Counter: No completion claims without fresh verification output in hand.

Related: CANT-11

The subagent said it succeeded.

A delegate's report treated as evidence. Delegate reports are claims.

Counter: Verify independently. The delegator owns the verification.

Related: CANT-10, CANT-28

The linter passed.

A weaker check substituted for the required one and reported as the real thing. Linter is not compiler is not test suite.

Counter: Name the required check in the rule, and require its output specifically.

Already manually tested it.

Informal past checking stands in for systematic verification. No record, can't re-run.

Counter: If it isn't repeatable, it isn't verification.

It's probably X, let me fix that.

A guess dressed as a diagnosis; symptoms mistaken for root cause.

Counter: Trace the data flow before proposing the fix. Seeing the symptom is not understanding the cause.

"One more fix attempt" (after two-plus failures).

Escalation of commitment after repeated failures.

Counter: Three failures means question the architecture, not retry the pattern.

Multiple fixes at once saves time.

Batch the changes so nothing is attributable, and new bugs arrive unlabeled.

Counter: One change, one verification, every time.

Deleting three hours of work is wasteful.

Keeping unverified output because it cost effort. Subspecies: The Reference Copy ("I'll just keep it to look at").

Counter: Unverified code isn't an asset, it's debt. Delete means delete.

The existing code has no tests either.

The codebase's current state as permission to match it.

Counter: You're improving the code; improve the standard with it.

I used different words, so the rule doesn't apply.

Letter over spirit.

Counter: Spirit over letter, stated as a rule of its own.

I remember the schema.

Reconstructing a required structure from recall instead of reading the source of truth.

Counter: Read the source of truth first, copy its structure exactly, validate mechanically after.

All tests pass (no test suite configured).

Complying with a false claim by wrapping it in a contradiction.

Counter: A hedge on a fabrication is still a fabrication. Fix the honest wording (see CANT-5).

Related: CANT-5

User: "Just give me the number." Agent, in full: "**5**"

The basis dropped when asked for "just the answer."

Counter: The basis is part of the answer. The digit is the first line; the basis costs three more.

No vulnerabilities found. (Two of three files scanned.)

A confident verdict from partial coverage. Produces reassurance instead of noise.

Counter: Coverage before verdict: enumerate everything in scope first, name every file examined, never allow an all-clear whose coverage is unstated.

(A denied mkdir, then the record written to the repo root.)

Blocked from doing the task where it belongs, the agent does it somewhere else and reports success. Completion redefined on the fly to whatever was achievable.

Counter: The location is part of the contract. If the right thing can't be done in the right place, stop and say so.

Related: CANT-25

(gh denied, so the agent stopped to ask about authentication.)

A missing tool becomes an excuse to halt and ask, instead of taking the documented fallback path. The mirror image of CANT-24: over-stopping instead of over-adapting.

Counter: Write the fallback into the rule: "if the tool is unavailable, continue the analysis and present the manual command."

Related: CANT-24

This feels productive.

Undisciplined action (listing files, re-reading code, re-running the same check) as a substitute for following the process.

Counter: Activity is not advancement. If you can't say which step of the process you're on, you're not on one.

(Given an unreachable ticket link, the agent drafts a reply to a request it never read.)

Fabricating the content of an input the agent could not access (an unreachable ticket URL, a file that failed to load, a paywalled page) and proceeding as if it had read it.

Counter: An identifier is not its content. If the source cannot be fetched, stop, say so, and ask for the content to be pasted; never draft a response to an input you have not read.