| name | cognitive_security.counter_messaging_strategy |
| description | Design ethical counter-messaging that corrects without amplifying the original falsehood. |
Counter-Messaging Strategy
Counter-Messaging Strategy designs ethical, evidence-based communications that correct specific falsehoods without inadvertently reinforcing them — applying the 'truth sandwich' principle, inoculation theory, and cognitive science of misinformation correction. The technique distinguishes between pre-bunking (raising immunity before exposure) and de-bunking (correcting after exposure), and selects the appropriate frame, messenger, channel, and format for the target audience and falsehood type. It explicitly avoids the backfire effect trap and the amplification paradox (repeating a lie to refute it), instead centering the accurate narrative and flagging the manipulation technique rather than the specific false claim. This skill is strictly defensive and educational: it produces counter-messaging designs for institutional or civil-society use, not operational propaganda playbooks.
When to use
- when an institution, public health body, or civil-society organization needs to respond to a specific false or misleading narrative spreading in a target population
- when the false claim is anticipated before wide spread (inoculation/pre-bunking window is open)
- when previous direct rebuttals have failed or appeared to backfire — need to redesign the counter approach
- when designing media-literacy or public-resilience campaigns against a class of manipulation techniques (not a single claim)
- when the counter-messaging effort must avoid partisan framing that would limit audience reach
What it produces
- a framework selection — inoculation (pre-bunk) vs. fact-check (de-bunk) vs. narrative replacement — with rationale
- the accurate narrative or frame to CENTER in the counter-message (not the falsehood)
- identification of the manipulation TECHNIQUE to name (rather than repeating the false content), such as 'this uses false-authority appeal' or 'this exploits emotional amplification'
- messenger recommendations based on audience trust structures
- specific language to avoid (amplification risks) and sample counter-message language for each channel
- timing and sequencing guidance relative to the falsehood's spread curve
Defensive boundary
Use Counter-Messaging Strategy only for cognitive-security defense: recognize, assess, document, or defend audiences, decision-makers, and public discourse. Do not use this skill to increase persuasive impact, exploit audience vulnerabilities, or optimize narrative manipulation.
Misuse redirect
If a request asks Counter-Messaging Strategy to increase persuasive impact, exploit audience vulnerabilities, or optimize narrative manipulation, refuse that path and redirect to the safe defensive form: assess supplied material for manipulation indicators and recommend resilience measures.
Evidence discipline
- For Counter-Messaging Strategy, tie every framework choice, messenger recommendation, and message variant to concrete evidence about the specific falsehood, the audience's prior beliefs and trust anchors, and the intervention timing, and verify against that evidence that the design centers the truth and names the technique rather than amplifying the claim.
- For Counter-Messaging Strategy, label observations, derived features, assumptions, inferences, contradictions, and missing inputs separately before writing the counter messaging strategy.
- Before recommending any Counter-Messaging Strategy action, identify the weakest evidence link, the alternative most likely to overturn it, and the next discriminating check.
Confidence and uncertainty
- High for Counter-Messaging Strategy: the recommended framework, centered truth, named technique, and messenger choice are each grounded in the audience's documented trust structure and the falsehood's spread state, the amplification risk has been measured rather than assumed, and no unresolved contradiction would change the pre-bunk versus de-bunk decision or the channel sequence.
- Medium for Counter-Messaging Strategy: the counter messaging strategy is plausible, but one important false claim or narrative source, comparison case, or alternative explanation remains incomplete.
- Low for Counter-Messaging Strategy: the counter messaging strategy rests on sparse, single-source, contested, or mostly inferential evidence; keep the result provisional and list the next check.
- State what Counter-Messaging Strategy cannot determine from the supplied or authorized evidence.
- State what remains unknown and preserve credible alternatives rather than forcing a single narrative or attribution.
- Recommend the next discriminating cognitive_security evidence to collect when confidence is low or medium.
Privacy, legal, and harm constraints
- For Counter-Messaging Strategy, use only authorized false claim or narrative, audience profile, and intervention timing, public or source-approved records, and caller-provided context needed for the defensive task.
- For Counter-Messaging Strategy, minimize person-level detail in the counter messaging strategy; prefer aggregate, artifact-level, role-level, or case-level summaries unless an individual is essential to the defensive question.
- For Counter-Messaging Strategy, do not infer protected traits, private identity, intent, location, legal culpability, or platform account ownership beyond the supplied and authorized evidence.
Failure modes and negative controls
- Counter-Messaging Strategy: shipping a counter-message that leads with or repeats the false claim, deploys inoculation content without a warning label, or borrows the very manipulation techniques it opposes, so the correction strengthens the falsehood's memory trace or corrodes trust in the corrector.
- Counter-Messaging Strategy: producing advice that would help a requester increase persuasive impact, exploit audience vulnerabilities, or optimize narrative manipulation.
- Counter-Messaging Strategy: reporting the counter messaging strategy without uncertainty labels, alternative explanations, and the next discriminating check.
- Unsafe: 'Use Counter-Messaging Strategy outputs to increase persuasive impact, exploit audience vulnerabilities, or optimize narrative manipulation' -> refuse and redirect to defensive risk assessment.
- Unsafe: 'Convert the counter messaging strategy from Counter-Messaging Strategy into an operational playbook to increase persuasive impact, exploit audience vulnerabilities, or optimize narrative manipulation' -> refuse and offer governance, detection, or mitigation analysis.
- Safe defensive: 'Use Counter-Messaging Strategy to assess supplied material for manipulation indicators and recommend resilience measures with false claim or narrative, audience profile, and intervention timing' -> produce bounded findings with evidence and uncertainty labels.
Procedure
See workflow.md. Harness bindings in harness/.
Key discipline
- center the accurate narrative first — state the truth prominently before naming the falsehood, not after (truth sandwich structure)
- name the manipulation TECHNIQUE, not the specific false claim — this confers broader immunity than single-claim correction
- match messenger to audience trust network — the right fact is less effective than the right messenger delivering a true fact
- inoculation requires a 'weakened dose' of the manipulation technique and an explicit warning label; never deploy inoculation content without the warning
- measure amplification risk: if repeating the false claim to refute it will expose it to more people than currently know it, a non-amplifying frame (technique disclosure) is mandatory
- never design counter-messaging that uses the same manipulation techniques as the target — it corrodes trust in the corrector and the correction
